diff options
131 files changed, 5196 insertions, 1690 deletions
diff --git a/.eslintrc.js b/.eslintrc.js index e3b4fb76..cf839769 100644 --- a/.eslintrc.js +++ b/.eslintrc.js @@ -74,6 +74,7 @@ module.exports = { create_submit_args: "readonly", restart_reload: "readonly", updateInput: "readonly", + onEdit: "readonly", //extraNetworks.js requestGet: "readonly", popup: "readonly", @@ -90,6 +91,8 @@ module.exports = { // localStorage.js localSet: "readonly", localGet: "readonly", - localRemove: "readonly" + localRemove: "readonly", + // resizeHandle.js + setupResizeHandle: "writable" } }; diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index d80b24e2..5876e941 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -1,35 +1,55 @@ name: Bug Report -description: You think somethings is broken in the UI +description: You think something is broken in the UI title: "[Bug]: " labels: ["bug-report"] body: + - type: markdown + attributes: + value: | + > The title of the bug report should be short and descriptive. + > Use relevant keywords for searchability. + > Do not leave it blank, but also do not put an entire error log in it. - type: checkboxes attributes: - label: Is there an existing issue for this? - description: Please search to see if an issue already exists for the bug you encountered, and that it hasn't been fixed in a recent build/commit. + label: Checklist + description: | + Please perform basic debugging to see if extensions or configuration is the cause of the issue. + Basic debug procedure + 1. Disable all third-party extensions - check if extension is the cause + 2. Update extensions and webui - sometimes things just need to be updated + 3. Backup and remove your config.json and ui-config.json - check if the issue is caused by bad configuration + 4. Delete venv with third-party extensions disabled - sometimes extensions might cause wrong libraries to be installed + 5. Try a fresh installation webui in a different directory - see if a clean installation solves the issue + Before making a issue report please, check that the issue hasn't been reported recently. options: - - label: I have searched the existing issues and checked the recent builds/commits - required: true + - label: The issue exists after disabling all extensions + - label: The issue exists on a clean installation of webui + - label: The issue is caused by an extension, but I believe it is caused by a bug in the webui + - label: The issue exists in the current version of the webui + - label: The issue has not been reported before recently + - label: The issue has been reported before but has not been fixed yet - type: markdown attributes: value: | - *Please fill this form with as much information as possible, don't forget to fill "What OS..." and "What browsers" and *provide screenshots if possible** + > Please fill this form with as much information as possible. Don't forget to "Upload Sysinfo" and "What browsers" and provide screenshots if possible - type: textarea id: what-did attributes: label: What happened? description: Tell us what happened in a very clear and simple way + placeholder: | + txt2img is not working as intended. validations: required: true - type: textarea id: steps attributes: label: Steps to reproduce the problem - description: Please provide us with precise step by step information on how to reproduce the bug - value: | - 1. Go to .... - 2. Press .... + description: Please provide us with precise step by step instructions on how to reproduce the bug + placeholder: | + 1. Go to ... + 2. Press ... 3. ... validations: required: true @@ -37,64 +57,9 @@ body: id: what-should attributes: label: What should have happened? - description: Tell what you think the normal behavior should be - validations: - required: true - - type: input - id: commit - attributes: - label: Version or Commit where the problem happens - description: "Which webui version or commit are you running ? (Do not write *Latest Version/repo/commit*, as this means nothing and will have changed by the time we read your issue. Rather, copy the **Version: v1.2.3** link at the bottom of the UI, or from the cmd/terminal if you can't launch it.)" - validations: - required: true - - type: dropdown - id: py-version - attributes: - label: What Python version are you running on ? - multiple: false - options: - - Python 3.10.x - - Python 3.11.x (above, no supported yet) - - Python 3.9.x (below, no recommended) - - type: dropdown - id: platforms - attributes: - label: What platforms do you use to access the UI ? - multiple: true - options: - - Windows - - Linux - - MacOS - - iOS - - Android - - Other/Cloud - - type: dropdown - id: device - attributes: - label: What device are you running WebUI on? - multiple: true - options: - - Nvidia GPUs (RTX 20 above) - - Nvidia GPUs (GTX 16 below) - - AMD GPUs (RX 6000 above) - - AMD GPUs (RX 5000 below) - - CPU - - Other GPUs - - type: dropdown - id: cross_attention_opt - attributes: - label: Cross attention optimization - description: What cross attention optimization are you using, Settings -> Optimizations -> Cross attention optimization - multiple: false - options: - - Automatic - - xformers - - sdp-no-mem - - sdp - - Doggettx - - V1 - - InvokeAI - - "None " + description: Tell us what you think the normal behavior should be + placeholder: | + WebUI should ... validations: required: true - type: dropdown @@ -108,26 +73,25 @@ body: - Brave - Apple Safari - Microsoft Edge + - Android + - iOS + - Other - type: textarea - id: cmdargs - attributes: - label: Command Line Arguments - description: Are you using any launching parameters/command line arguments (modified webui-user .bat/.sh) ? If yes, please write them below. Write "No" otherwise. - render: Shell - validations: - required: true - - type: textarea - id: extensions + id: sysinfo attributes: - label: List of extensions - description: Are you using any extensions other than built-ins? If yes, provide a list, you can copy it at "Extensions" tab. Write "No" otherwise. + label: Sysinfo + description: System info file, generated by WebUI. You can generate it in settings, on the Sysinfo page. Drag the file into the field to upload it. If you submit your report without including the sysinfo file, the report will be closed. If needed, review the report to make sure it includes no personal information you don't want to share. If you can't start WebUI, you can use --dump-sysinfo commandline argument to generate the file. + placeholder: | + 1. Go to WebUI Settings -> Sysinfo -> Download system info. + If WebUI fails to launch, use --dump-sysinfo commandline argument to generate the file + 2. Upload the Sysinfo as a attached file, Do NOT paste it in as plain text. validations: required: true - type: textarea id: logs attributes: label: Console logs - description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after your bug happened. If it's very long, provide a link to pastebin or similar service. + description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after the bug occured. If it's very long, provide a link to pastebin or similar service. render: Shell validations: required: true @@ -135,4 +99,7 @@ body: id: misc attributes: label: Additional information - description: Please provide us with any relevant additional info or context. + description: | + Please provide us with any relevant additional info or context. + Examples: + I have updated my GPU driver recently. diff --git a/CHANGELOG.md b/CHANGELOG.md index b18c6867..2c72359f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,163 @@ +## 1.6.1
+
+### Bug Fixes:
+ * fix an error causing the webui to fail to start ([#13839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13839))
+
+## 1.6.0
+
+### Features:
+ * refiner support [#12371](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12371)
+ * add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards
+ * add style editor dialog
+ * hires fix: add an option to use a different checkpoint for second pass ([#12181](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12181))
+ * option to keep multiple loaded models in memory ([#12227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12227))
+ * new samplers: Restart, DPM++ 2M SDE Exponential, DPM++ 2M SDE Heun, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 3M SDE Exponential ([#12300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12300), [#12519](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12519), [#12542](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12542))
+ * rework DDIM, PLMS, UniPC to use CFG denoiser same as in k-diffusion samplers:
+ * makes all of them work with img2img
+ * makes prompt composition posssible (AND)
+ * makes them available for SDXL
+ * always show extra networks tabs in the UI ([#11808](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11808))
+ * use less RAM when creating models ([#11958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11958), [#12599](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12599))
+ * textual inversion inference support for SDXL
+ * extra networks UI: show metadata for SD checkpoints
+ * checkpoint merger: add metadata support
+ * prompt editing and attention: add support for whitespace after the number ([ red : green : 0.5 ]) (seed breaking change) ([#12177](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12177))
+ * VAE: allow selecting own VAE for each checkpoint (in user metadata editor)
+ * VAE: add selected VAE to infotext
+ * options in main UI: add own separate setting for txt2img and img2img, correctly read values from pasted infotext, add setting for column count ([#12551](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12551))
+ * add resize handle to txt2img and img2img tabs, allowing to change the amount of horizontable space given to generation parameters and resulting image gallery ([#12687](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12687), [#12723](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12723))
+ * change default behavior for batching cond/uncond -- now it's on by default, and is disabled by an UI setting (Optimizatios -> Batch cond/uncond) - if you are on lowvram/medvram and are getting OOM exceptions, you will need to enable it
+ * show current position in queue and make it so that requests are processed in the order of arrival ([#12707](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12707))
+ * add `--medvram-sdxl` flag that only enables `--medvram` for SDXL models
+ * prompt editing timeline has separate range for first pass and hires-fix pass (seed breaking change) ([#12457](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12457))
+
+### Minor:
+ * img2img batch: RAM savings, VRAM savings, .tif, .tiff in img2img batch ([#12120](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12120), [#12514](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12514), [#12515](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12515))
+ * postprocessing/extras: RAM savings ([#12479](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12479))
+ * XYZ: in the axis labels, remove pathnames from model filenames
+ * XYZ: support hires sampler ([#12298](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12298))
+ * XYZ: new option: use text inputs instead of dropdowns ([#12491](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12491))
+ * add gradio version warning
+ * sort list of VAE checkpoints ([#12297](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12297))
+ * use transparent white for mask in inpainting, along with an option to select the color ([#12326](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12326))
+ * move some settings to their own section: img2img, VAE
+ * add checkbox to show/hide dirs for extra networks
+ * Add TAESD(or more) options for all the VAE encode/decode operation ([#12311](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12311))
+ * gradio theme cache, new gradio themes, along with explanation that the user can input his own values ([#12346](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12346), [#12355](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12355))
+ * sampler fixes/tweaks: s_tmax, s_churn, s_noise, s_tmax ([#12354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12354), [#12356](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12356), [#12357](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12357), [#12358](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12358), [#12375](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12375), [#12521](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12521))
+ * update README.md with correct instructions for Linux installation ([#12352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12352))
+ * option to not save incomplete images, on by default ([#12338](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12338))
+ * enable cond cache by default
+ * git autofix for repos that are corrupted ([#12230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12230))
+ * allow to open images in new browser tab by middle mouse button ([#12379](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12379))
+ * automatically open webui in browser when running "locally" ([#12254](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12254))
+ * put commonly used samplers on top, make DPM++ 2M Karras the default choice
+ * zoom and pan: option to auto-expand a wide image, improved integration ([#12413](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12413), [#12727](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12727))
+ * option to cache Lora networks in memory
+ * rework hires fix UI to use accordion
+ * face restoration and tiling moved to settings - use "Options in main UI" setting if you want them back
+ * change quicksettings items to have variable width
+ * Lora: add Norm module, add support for bias ([#12503](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12503))
+ * Lora: output warnings in UI rather than fail for unfitting loras; switch to logging for error output in console
+ * support search and display of hashes for all extra network items ([#12510](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12510))
+ * add extra noise param for img2img operations ([#12564](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12564))
+ * support for Lora with bias ([#12584](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12584))
+ * make interrupt quicker ([#12634](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12634))
+ * configurable gallery height ([#12648](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12648))
+ * make results column sticky ([#12645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12645))
+ * more hash filename patterns ([#12639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12639))
+ * make image viewer actually fit the whole page ([#12635](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12635))
+ * make progress bar work independently from live preview display which results in it being updated a lot more often
+ * forbid Full live preview method for medvram and add a setting to undo the forbidding
+ * make it possible to localize tooltips and placeholders
+ * add option to align with sgm repo's sampling implementation ([#12818](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818))
+ * Restore faces and Tiling generation parameters have been moved to settings out of main UI
+ * if you want to put them back into main UI, use `Options in main UI` setting on the UI page.
+
+### Extensions and API:
+ * gradio 3.41.2
+ * also bump versions for packages: transformers, GitPython, accelerate, scikit-image, timm, tomesd
+ * support tooltip kwarg for gradio elements: gr.Textbox(label='hello', tooltip='world')
+ * properly clear the total console progressbar when using txt2img and img2img from API
+ * add cmd_arg --disable-extra-extensions and --disable-all-extensions ([#12294](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12294))
+ * shared.py and webui.py split into many files
+ * add --loglevel commandline argument for logging
+ * add a custom UI element that combines accordion and checkbox
+ * avoid importing gradio in tests because it spams warnings
+ * put infotext label for setting into OptionInfo definition rather than in a separate list
+ * make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur` ([#12470](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12470))
+ * option to make scripts UI without gr.Group
+ * add a way for scripts to register a callback for before/after just a single component's creation
+ * use dataclass for StableDiffusionProcessing
+ * store patches for Lora in a specialized module instead of inside torch
+ * support http/https URLs in API ([#12663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12663), [#12698](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12698))
+ * add extra noise callback ([#12616](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12616))
+ * dump current stack traces when exiting with SIGINT
+ * add type annotations for extra fields of shared.sd_model
+
+### Bug Fixes:
+ * Don't crash if out of local storage quota for javascriot localStorage
+ * XYZ plot do not fail if an exception occurs
+ * fix missing TI hash in infotext if generation uses both negative and positive TI ([#12269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12269))
+ * localization fixes ([#12307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12307))
+ * fix sdxl model invalid configuration after the hijack
+ * correctly toggle extras checkbox for infotext paste ([#12304](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12304))
+ * open raw sysinfo link in new page ([#12318](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12318))
+ * prompt parser: Account for empty field in alternating words syntax ([#12319](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12319))
+ * add tab and carriage return to invalid filename chars ([#12327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12327))
+ * fix api only Lora not working ([#12387](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12387))
+ * fix options in main UI misbehaving when there's just one element
+ * make it possible to use a sampler from infotext even if it's hidden in the dropdown
+ * fix styles missing from the prompt in infotext when making a grid of batch of multiplie images
+ * prevent bogus progress output in console when calculating hires fix dimensions
+ * fix --use-textbox-seed
+ * fix broken `Lora/Networks: use old method` option ([#12466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12466))
+ * properly return `None` for VAE hash when using `--no-hashing` ([#12463](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12463))
+ * MPS/macOS fixes and optimizations ([#12526](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12526))
+ * add second_order to samplers that mistakenly didn't have it
+ * when refreshing cards in extra networks UI, do not discard user's custom resolution
+ * fix processing error that happens if batch_size is not a multiple of how many prompts/negative prompts there are ([#12509](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12509))
+ * fix inpaint upload for alpha masks ([#12588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12588))
+ * fix exception when image sizes are not integers ([#12586](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12586))
+ * fix incorrect TAESD Latent scale ([#12596](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12596))
+ * auto add data-dir to gradio-allowed-path ([#12603](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12603))
+ * fix exception if extensuions dir is missing ([#12607](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12607))
+ * fix issues with api model-refresh and vae-refresh ([#12638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12638))
+ * fix img2img background color for transparent images option not being used ([#12633](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12633))
+ * attempt to resolve NaN issue with unstable VAEs in fp32 mk2 ([#12630](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12630))
+ * implement missing undo hijack for SDXL
+ * fix xyz swap axes ([#12684](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12684))
+ * fix errors in backup/restore tab if any of config files are broken ([#12689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12689))
+ * fix SD VAE switch error after model reuse ([#12685](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12685))
+ * fix trying to create images too large for the chosen format ([#12667](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12667))
+ * create Gradio temp directory if necessary ([#12717](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12717))
+ * prevent possible cache loss if exiting as it's being written by using an atomic operation to replace the cache with the new version
+ * set devices.dtype_unet correctly
+ * run RealESRGAN on GPU for non-CUDA devices ([#12737](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
+ * prevent extra network buttons being obscured by description for very small card sizes ([#12745](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12745))
+ * fix error that causes some extra networks to be disabled if both <lora:> and <lyco:> are present in the prompt
+ * fix defaults settings page breaking when any of main UI tabs are hidden
+ * fix incorrect save/display of new values in Defaults page in settings
+ * fix for Reload UI function: if you reload UI on one tab, other opened tabs will no longer stop working
+ * fix an error that prevents VAE being reloaded after an option change if a VAE near the checkpoint exists ([#12797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
+ * hide broken image crop tool ([#12792](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
+ * don't show hidden samplers in dropdown for XYZ script ([#12780](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
+ * fix style editing dialog breaking if it's opened in both img2img and txt2img tabs
+ * fix a bug allowing users to bypass gradio and API authentication (reported by vysecurity)
+ * fix notification not playing when built-in webui tab is inactive ([#12834](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12834))
+ * honor `--skip-install` for extension installers ([#12832](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832))
+ * don't print blank stdout in extension installers ([#12833](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832), [#12855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12855))
+ * do not change quicksettings dropdown option when value returned is `None` ([#12854](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12854))
+ * get progressbar to display correctly in extensions tab
+
+
+## 1.5.2
+
+### Bug Fixes:
+ * fix memory leak when generation fails
+ * update doggettx cross attention optimization to not use an unreasonable amount of memory in some edge cases -- suggestion by MorkTheOrk
+
+
## 1.5.1
### Minor:
diff --git a/CITATION.cff b/CITATION.cff new file mode 100644 index 00000000..2c781aff --- /dev/null +++ b/CITATION.cff @@ -0,0 +1,7 @@ +cff-version: 1.2.0 +message: "If you use this software, please cite it as below." +authors: + - given-names: AUTOMATIC1111 +title: "Stable Diffusion Web UI" +date-released: 2022-08-22 +url: "https://github.com/AUTOMATIC1111/stable-diffusion-webui" @@ -78,7 +78,7 @@ A browser interface based on Gradio library for Stable Diffusion. - Clip skip
- Hypernetworks
- Loras (same as Hypernetworks but more pretty)
-- A sparate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
+- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
- Can select to load a different VAE from settings screen
- Estimated completion time in progress bar
- API
@@ -88,19 +88,23 @@ A browser interface based on Gradio library for Stable Diffusion. - [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
- Now without any bad letters!
- Load checkpoints in safetensors format
-- Eased resolution restriction: generated image's dimension must be a multiple of 8 rather than 64
+- Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64
- Now with a license!
- Reorder elements in the UI from settings screen
+- [Segmind Stable Diffusion](https://huggingface.co/segmind/SSD-1B) support
## Installation and Running
-Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
+Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for:
+- [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended)
+- [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
+- [Intel CPUs, Intel GPUs (both integrated and discrete)](https://github.com/openvinotoolkit/stable-diffusion-webui/wiki/Installation-on-Intel-Silicon) (external wiki page)
Alternatively, use online services (like Google Colab):
- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
### Installation on Windows 10/11 with NVidia-GPUs using release package
-1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre) and extract it's contents.
+1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre) and extract its contents.
2. Run `update.bat`.
3. Run `run.bat`.
> For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs)
@@ -143,7 +147,7 @@ For the purposes of getting Google and other search engines to crawl the wiki, h ## Credits
Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
-- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
+- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers
- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
- GFPGAN - https://github.com/TencentARC/GFPGAN.git
- CodeFormer - https://github.com/sczhou/CodeFormer
@@ -170,5 +174,6 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al - TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
- LyCORIS - KohakuBlueleaf
- Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
+- Hypertile - tfernd - https://github.com/tfernd/HyperTile
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- (You)
diff --git a/configs/alt-diffusion-m18-inference.yaml b/configs/alt-diffusion-m18-inference.yaml new file mode 100644 index 00000000..41a031d5 --- /dev/null +++ b/configs/alt-diffusion-m18-inference.yaml @@ -0,0 +1,73 @@ +model: + base_learning_rate: 1.0e-04 + target: ldm.models.diffusion.ddpm.LatentDiffusion + params: + linear_start: 0.00085 + linear_end: 0.0120 + num_timesteps_cond: 1 + log_every_t: 200 + timesteps: 1000 + first_stage_key: "jpg" + cond_stage_key: "txt" + image_size: 64 + channels: 4 + cond_stage_trainable: false # Note: different from the one we trained before + conditioning_key: crossattn + monitor: val/loss_simple_ema + scale_factor: 0.18215 + use_ema: False + + scheduler_config: # 10000 warmup steps + target: ldm.lr_scheduler.LambdaLinearScheduler + params: + warm_up_steps: [ 10000 ] + cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases + f_start: [ 1.e-6 ] + f_max: [ 1. ] + f_min: [ 1. ] + + unet_config: + target: ldm.modules.diffusionmodules.openaimodel.UNetModel + params: + image_size: 32 # unused + in_channels: 4 + out_channels: 4 + model_channels: 320 + attention_resolutions: [ 4, 2, 1 ] + num_res_blocks: 2 + channel_mult: [ 1, 2, 4, 4 ] + num_head_channels: 64 + use_spatial_transformer: True + use_linear_in_transformer: True + transformer_depth: 1 + context_dim: 1024 + use_checkpoint: True + legacy: False + + first_stage_config: + target: ldm.models.autoencoder.AutoencoderKL + params: + embed_dim: 4 + monitor: val/rec_loss + ddconfig: + double_z: true + z_channels: 4 + resolution: 256 + in_channels: 3 + out_ch: 3 + ch: 128 + ch_mult: + - 1 + - 2 + - 4 + - 4 + num_res_blocks: 2 + attn_resolutions: [] + dropout: 0.0 + lossconfig: + target: torch.nn.Identity + + cond_stage_config: + target: modules.xlmr_m18.BertSeriesModelWithTransformation + params: + name: "XLMR-Large" diff --git a/extensions-builtin/Lora/extra_networks_lora.py b/extensions-builtin/Lora/extra_networks_lora.py index ba2945c6..005ff32c 100644 --- a/extensions-builtin/Lora/extra_networks_lora.py +++ b/extensions-builtin/Lora/extra_networks_lora.py @@ -6,9 +6,14 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork): def __init__(self):
super().__init__('lora')
+ self.errors = {}
+ """mapping of network names to the number of errors the network had during operation"""
+
def activate(self, p, params_list):
additional = shared.opts.sd_lora
+ self.errors.clear()
+
if additional != "None" and additional in networks.available_networks and not any(x for x in params_list if x.items[0] == additional):
p.all_prompts = [x + f"<lora:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
@@ -56,4 +61,7 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork): p.extra_generation_params["Lora hashes"] = ", ".join(network_hashes)
def deactivate(self, p):
- pass
+ if self.errors:
+ p.comment("Networks with errors: " + ", ".join(f"{k} ({v})" for k, v in self.errors.items()))
+
+ self.errors.clear()
diff --git a/extensions-builtin/Lora/lora_logger.py b/extensions-builtin/Lora/lora_logger.py new file mode 100644 index 00000000..d51de297 --- /dev/null +++ b/extensions-builtin/Lora/lora_logger.py @@ -0,0 +1,33 @@ +import sys +import copy +import logging + + +class ColoredFormatter(logging.Formatter): + COLORS = { + "DEBUG": "\033[0;36m", # CYAN + "INFO": "\033[0;32m", # GREEN + "WARNING": "\033[0;33m", # YELLOW + "ERROR": "\033[0;31m", # RED + "CRITICAL": "\033[0;37;41m", # WHITE ON RED + "RESET": "\033[0m", # RESET COLOR + } + + def format(self, record): + colored_record = copy.copy(record) + levelname = colored_record.levelname + seq = self.COLORS.get(levelname, self.COLORS["RESET"]) + colored_record.levelname = f"{seq}{levelname}{self.COLORS['RESET']}" + return super().format(colored_record) + + +logger = logging.getLogger("lora") +logger.propagate = False + + +if not logger.handlers: + handler = logging.StreamHandler(sys.stdout) + handler.setFormatter( + ColoredFormatter("[%(name)s]-%(levelname)s: %(message)s") + ) + logger.addHandler(handler) diff --git a/extensions-builtin/Lora/lora_patches.py b/extensions-builtin/Lora/lora_patches.py new file mode 100644 index 00000000..b394d8e9 --- /dev/null +++ b/extensions-builtin/Lora/lora_patches.py @@ -0,0 +1,31 @@ +import torch
+
+import networks
+from modules import patches
+
+
+class LoraPatches:
+ def __init__(self):
+ self.Linear_forward = patches.patch(__name__, torch.nn.Linear, 'forward', networks.network_Linear_forward)
+ self.Linear_load_state_dict = patches.patch(__name__, torch.nn.Linear, '_load_from_state_dict', networks.network_Linear_load_state_dict)
+ self.Conv2d_forward = patches.patch(__name__, torch.nn.Conv2d, 'forward', networks.network_Conv2d_forward)
+ self.Conv2d_load_state_dict = patches.patch(__name__, torch.nn.Conv2d, '_load_from_state_dict', networks.network_Conv2d_load_state_dict)
+ self.GroupNorm_forward = patches.patch(__name__, torch.nn.GroupNorm, 'forward', networks.network_GroupNorm_forward)
+ self.GroupNorm_load_state_dict = patches.patch(__name__, torch.nn.GroupNorm, '_load_from_state_dict', networks.network_GroupNorm_load_state_dict)
+ self.LayerNorm_forward = patches.patch(__name__, torch.nn.LayerNorm, 'forward', networks.network_LayerNorm_forward)
+ self.LayerNorm_load_state_dict = patches.patch(__name__, torch.nn.LayerNorm, '_load_from_state_dict', networks.network_LayerNorm_load_state_dict)
+ self.MultiheadAttention_forward = patches.patch(__name__, torch.nn.MultiheadAttention, 'forward', networks.network_MultiheadAttention_forward)
+ self.MultiheadAttention_load_state_dict = patches.patch(__name__, torch.nn.MultiheadAttention, '_load_from_state_dict', networks.network_MultiheadAttention_load_state_dict)
+
+ def undo(self):
+ self.Linear_forward = patches.undo(__name__, torch.nn.Linear, 'forward')
+ self.Linear_load_state_dict = patches.undo(__name__, torch.nn.Linear, '_load_from_state_dict')
+ self.Conv2d_forward = patches.undo(__name__, torch.nn.Conv2d, 'forward')
+ self.Conv2d_load_state_dict = patches.undo(__name__, torch.nn.Conv2d, '_load_from_state_dict')
+ self.GroupNorm_forward = patches.undo(__name__, torch.nn.GroupNorm, 'forward')
+ self.GroupNorm_load_state_dict = patches.undo(__name__, torch.nn.GroupNorm, '_load_from_state_dict')
+ self.LayerNorm_forward = patches.undo(__name__, torch.nn.LayerNorm, 'forward')
+ self.LayerNorm_load_state_dict = patches.undo(__name__, torch.nn.LayerNorm, '_load_from_state_dict')
+ self.MultiheadAttention_forward = patches.undo(__name__, torch.nn.MultiheadAttention, 'forward')
+ self.MultiheadAttention_load_state_dict = patches.undo(__name__, torch.nn.MultiheadAttention, '_load_from_state_dict')
+
diff --git a/extensions-builtin/Lora/lyco_helpers.py b/extensions-builtin/Lora/lyco_helpers.py index 279b34bc..1679a0ce 100644 --- a/extensions-builtin/Lora/lyco_helpers.py +++ b/extensions-builtin/Lora/lyco_helpers.py @@ -19,3 +19,50 @@ def rebuild_cp_decomposition(up, down, mid): up = up.reshape(up.size(0), -1)
down = down.reshape(down.size(0), -1)
return torch.einsum('n m k l, i n, m j -> i j k l', mid, up, down)
+
+
+# copied from https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/lokr.py
+def factorization(dimension: int, factor:int=-1) -> tuple[int, int]:
+ '''
+ return a tuple of two value of input dimension decomposed by the number closest to factor
+ second value is higher or equal than first value.
+
+ In LoRA with Kroneckor Product, first value is a value for weight scale.
+ secon value is a value for weight.
+
+ Becuase of non-commutative property, A⊗B ≠ B⊗A. Meaning of two matrices is slightly different.
+
+ examples)
+ factor
+ -1 2 4 8 16 ...
+ 127 -> 1, 127 127 -> 1, 127 127 -> 1, 127 127 -> 1, 127 127 -> 1, 127
+ 128 -> 8, 16 128 -> 2, 64 128 -> 4, 32 128 -> 8, 16 128 -> 8, 16
+ 250 -> 10, 25 250 -> 2, 125 250 -> 2, 125 250 -> 5, 50 250 -> 10, 25
+ 360 -> 8, 45 360 -> 2, 180 360 -> 4, 90 360 -> 8, 45 360 -> 12, 30
+ 512 -> 16, 32 512 -> 2, 256 512 -> 4, 128 512 -> 8, 64 512 -> 16, 32
+ 1024 -> 32, 32 1024 -> 2, 512 1024 -> 4, 256 1024 -> 8, 128 1024 -> 16, 64
+ '''
+
+ if factor > 0 and (dimension % factor) == 0:
+ m = factor
+ n = dimension // factor
+ if m > n:
+ n, m = m, n
+ return m, n
+ if factor < 0:
+ factor = dimension
+ m, n = 1, dimension
+ length = m + n
+ while m<n:
+ new_m = m + 1
+ while dimension%new_m != 0:
+ new_m += 1
+ new_n = dimension // new_m
+ if new_m + new_n > length or new_m>factor:
+ break
+ else:
+ m, n = new_m, new_n
+ if m > n:
+ n, m = m, n
+ return m, n
+
diff --git a/extensions-builtin/Lora/network.py b/extensions-builtin/Lora/network.py index 0a18d69e..6021fd8d 100644 --- a/extensions-builtin/Lora/network.py +++ b/extensions-builtin/Lora/network.py @@ -93,6 +93,7 @@ class Network: # LoraModule self.unet_multiplier = 1.0
self.dyn_dim = None
self.modules = {}
+ self.bundle_embeddings = {}
self.mtime = None
self.mentioned_name = None
@@ -133,7 +134,7 @@ class NetworkModule: return 1.0
- def finalize_updown(self, updown, orig_weight, output_shape):
+ def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None):
if self.bias is not None:
updown = updown.reshape(self.bias.shape)
updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype)
@@ -145,7 +146,10 @@ class NetworkModule: if orig_weight.size().numel() == updown.size().numel():
updown = updown.reshape(orig_weight.shape)
- return updown * self.calc_scale() * self.multiplier()
+ if ex_bias is not None:
+ ex_bias = ex_bias * self.multiplier()
+
+ return updown * self.calc_scale() * self.multiplier(), ex_bias
def calc_updown(self, target):
raise NotImplementedError()
diff --git a/extensions-builtin/Lora/network_full.py b/extensions-builtin/Lora/network_full.py index 109b4c2c..bf6930e9 100644 --- a/extensions-builtin/Lora/network_full.py +++ b/extensions-builtin/Lora/network_full.py @@ -14,9 +14,14 @@ class NetworkModuleFull(network.NetworkModule): super().__init__(net, weights)
self.weight = weights.w.get("diff")
+ self.ex_bias = weights.w.get("diff_b")
def calc_updown(self, orig_weight):
output_shape = self.weight.shape
updown = self.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+ if self.ex_bias is not None:
+ ex_bias = self.ex_bias.to(orig_weight.device, dtype=orig_weight.dtype)
+ else:
+ ex_bias = None
- return self.finalize_updown(updown, orig_weight, output_shape)
+ return self.finalize_updown(updown, orig_weight, output_shape, ex_bias)
diff --git a/extensions-builtin/Lora/network_glora.py b/extensions-builtin/Lora/network_glora.py new file mode 100644 index 00000000..492d4870 --- /dev/null +++ b/extensions-builtin/Lora/network_glora.py @@ -0,0 +1,33 @@ + +import network + +class ModuleTypeGLora(network.ModuleType): + def create_module(self, net: network.Network, weights: network.NetworkWeights): + if all(x in weights.w for x in ["a1.weight", "a2.weight", "alpha", "b1.weight", "b2.weight"]): + return NetworkModuleGLora(net, weights) + + return None + +# adapted from https://github.com/KohakuBlueleaf/LyCORIS +class NetworkModuleGLora(network.NetworkModule): + def __init__(self, net: network.Network, weights: network.NetworkWeights): + super().__init__(net, weights) + + if hasattr(self.sd_module, 'weight'): + self.shape = self.sd_module.weight.shape + + self.w1a = weights.w["a1.weight"] + self.w1b = weights.w["b1.weight"] + self.w2a = weights.w["a2.weight"] + self.w2b = weights.w["b2.weight"] + + def calc_updown(self, orig_weight): + w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype) + w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype) + w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype) + w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype) + + output_shape = [w1a.size(0), w1b.size(1)] + updown = ((w2b @ w1b) + ((orig_weight @ w2a) @ w1a)) + + return self.finalize_updown(updown, orig_weight, output_shape) diff --git a/extensions-builtin/Lora/network_norm.py b/extensions-builtin/Lora/network_norm.py new file mode 100644 index 00000000..ce450158 --- /dev/null +++ b/extensions-builtin/Lora/network_norm.py @@ -0,0 +1,28 @@ +import network + + +class ModuleTypeNorm(network.ModuleType): + def create_module(self, net: network.Network, weights: network.NetworkWeights): + if all(x in weights.w for x in ["w_norm", "b_norm"]): + return NetworkModuleNorm(net, weights) + + return None + + +class NetworkModuleNorm(network.NetworkModule): + def __init__(self, net: network.Network, weights: network.NetworkWeights): + super().__init__(net, weights) + + self.w_norm = weights.w.get("w_norm") + self.b_norm = weights.w.get("b_norm") + + def calc_updown(self, orig_weight): + output_shape = self.w_norm.shape + updown = self.w_norm.to(orig_weight.device, dtype=orig_weight.dtype) + + if self.b_norm is not None: + ex_bias = self.b_norm.to(orig_weight.device, dtype=orig_weight.dtype) + else: + ex_bias = None + + return self.finalize_updown(updown, orig_weight, output_shape, ex_bias) diff --git a/extensions-builtin/Lora/network_oft.py b/extensions-builtin/Lora/network_oft.py new file mode 100644 index 00000000..05c37811 --- /dev/null +++ b/extensions-builtin/Lora/network_oft.py @@ -0,0 +1,97 @@ +import torch +import network +from lyco_helpers import factorization +from einops import rearrange + + +class ModuleTypeOFT(network.ModuleType): + def create_module(self, net: network.Network, weights: network.NetworkWeights): + if all(x in weights.w for x in ["oft_blocks"]) or all(x in weights.w for x in ["oft_diag"]): + return NetworkModuleOFT(net, weights) + + return None + +# Supports both kohya-ss' implementation of COFT https://github.com/kohya-ss/sd-scripts/blob/main/networks/oft.py +# and KohakuBlueleaf's implementation of OFT/COFT https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/diag_oft.py +class NetworkModuleOFT(network.NetworkModule): + def __init__(self, net: network.Network, weights: network.NetworkWeights): + + super().__init__(net, weights) + + self.lin_module = None + self.org_module: list[torch.Module] = [self.sd_module] + + # kohya-ss + if "oft_blocks" in weights.w.keys(): + self.is_kohya = True + self.oft_blocks = weights.w["oft_blocks"] # (num_blocks, block_size, block_size) + self.alpha = weights.w["alpha"] # alpha is constraint + self.dim = self.oft_blocks.shape[0] # lora dim + # LyCORIS + elif "oft_diag" in weights.w.keys(): + self.is_kohya = False + self.oft_blocks = weights.w["oft_diag"] + # self.alpha is unused + self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size) + + is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear] + is_conv = type(self.sd_module) in [torch.nn.Conv2d] + is_other_linear = type(self.sd_module) in [torch.nn.MultiheadAttention] # unsupported + + if is_linear: + self.out_dim = self.sd_module.out_features + elif is_conv: + self.out_dim = self.sd_module.out_channels + elif is_other_linear: + self.out_dim = self.sd_module.embed_dim + + if self.is_kohya: + self.constraint = self.alpha * self.out_dim + self.num_blocks = self.dim + self.block_size = self.out_dim // self.dim + else: + self.constraint = None + self.block_size, self.num_blocks = factorization(self.out_dim, self.dim) + + def calc_updown_kb(self, orig_weight, multiplier): + oft_blocks = self.oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype) + oft_blocks = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix + + R = oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype) + R = R * multiplier + torch.eye(self.block_size, device=orig_weight.device) + + # This errors out for MultiheadAttention, might need to be handled up-stream + merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size) + merged_weight = torch.einsum( + 'k n m, k n ... -> k m ...', + R, + merged_weight + ) + merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...') + + updown = merged_weight.to(orig_weight.device, dtype=orig_weight.dtype) - orig_weight + output_shape = orig_weight.shape + return self.finalize_updown(updown, orig_weight, output_shape) + + def calc_updown(self, orig_weight): + # if alpha is a very small number as in coft, calc_scale() will return a almost zero number so we ignore it + multiplier = self.multiplier() + return self.calc_updown_kb(orig_weight, multiplier) + + # override to remove the multiplier/scale factor; it's already multiplied in get_weight + def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None): + if self.bias is not None: + updown = updown.reshape(self.bias.shape) + updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype) + updown = updown.reshape(output_shape) + + if len(output_shape) == 4: + updown = updown.reshape(output_shape) + + if orig_weight.size().numel() == updown.size().numel(): + updown = updown.reshape(orig_weight.shape) + + if ex_bias is not None: + ex_bias = ex_bias * self.multiplier() + + return updown, ex_bias diff --git a/extensions-builtin/Lora/networks.py b/extensions-builtin/Lora/networks.py index bc722e90..7f814706 100644 --- a/extensions-builtin/Lora/networks.py +++ b/extensions-builtin/Lora/networks.py @@ -1,17 +1,25 @@ +import logging
import os
import re
+import lora_patches
import network
import network_lora
+import network_glora
import network_hada
import network_ia3
import network_lokr
import network_full
+import network_norm
+import network_oft
import torch
from typing import Union
from modules import shared, devices, sd_models, errors, scripts, sd_hijack
+import modules.textual_inversion.textual_inversion as textual_inversion
+
+from lora_logger import logger
module_types = [
network_lora.ModuleTypeLora(),
@@ -19,6 +27,9 @@ module_types = [ network_ia3.ModuleTypeIa3(),
network_lokr.ModuleTypeLokr(),
network_full.ModuleTypeFull(),
+ network_norm.ModuleTypeNorm(),
+ network_glora.ModuleTypeGLora(),
+ network_oft.ModuleTypeOFT(),
]
@@ -31,6 +42,8 @@ suffix_conversion = { "resnets": {
"conv1": "in_layers_2",
"conv2": "out_layers_3",
+ "norm1": "in_layers_0",
+ "norm2": "out_layers_0",
"time_emb_proj": "emb_layers_1",
"conv_shortcut": "skip_connection",
}
@@ -143,9 +156,19 @@ def load_network(name, network_on_disk): is_sd2 = 'model_transformer_resblocks' in shared.sd_model.network_layer_mapping
matched_networks = {}
+ bundle_embeddings = {}
for key_network, weight in sd.items():
key_network_without_network_parts, network_part = key_network.split(".", 1)
+ if key_network_without_network_parts == "bundle_emb":
+ emb_name, vec_name = network_part.split(".", 1)
+ emb_dict = bundle_embeddings.get(emb_name, {})
+ if vec_name.split('.')[0] == 'string_to_param':
+ _, k2 = vec_name.split('.', 1)
+ emb_dict['string_to_param'] = {k2: weight}
+ else:
+ emb_dict[vec_name] = weight
+ bundle_embeddings[emb_name] = emb_dict
key = convert_diffusers_name_to_compvis(key_network_without_network_parts, is_sd2)
sd_module = shared.sd_model.network_layer_mapping.get(key, None)
@@ -168,6 +191,17 @@ def load_network(name, network_on_disk): key = key_network_without_network_parts.replace("lora_te1_text_model", "transformer_text_model")
sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+ # kohya_ss OFT module
+ elif sd_module is None and "oft_unet" in key_network_without_network_parts:
+ key = key_network_without_network_parts.replace("oft_unet", "diffusion_model")
+ sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+ # KohakuBlueLeaf OFT module
+ if sd_module is None and "oft_diag" in key:
+ key = key_network_without_network_parts.replace("lora_unet", "diffusion_model")
+ key = key_network_without_network_parts.replace("lora_te1_text_model", "0_transformer_text_model")
+ sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
if sd_module is None:
keys_failed_to_match[key_network] = key
continue
@@ -189,8 +223,16 @@ def load_network(name, network_on_disk): net.modules[key] = net_module
+ embeddings = {}
+ for emb_name, data in bundle_embeddings.items():
+ embedding = textual_inversion.create_embedding_from_data(data, emb_name, filename=network_on_disk.filename + "/" + emb_name)
+ embedding.loaded = None
+ embeddings[emb_name] = embedding
+
+ net.bundle_embeddings = embeddings
+
if keys_failed_to_match:
- print(f"Failed to match keys when loading network {network_on_disk.filename}: {keys_failed_to_match}")
+ logging.debug(f"Network {network_on_disk.filename} didn't match keys: {keys_failed_to_match}")
return net
@@ -203,13 +245,16 @@ def purge_networks_from_memory(): devices.torch_gc()
-
def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=None):
+ emb_db = sd_hijack.model_hijack.embedding_db
already_loaded = {}
for net in loaded_networks:
if net.name in names:
already_loaded[net.name] = net
+ for emb_name, embedding in net.bundle_embeddings.items():
+ if embedding.loaded:
+ emb_db.register_embedding_by_name(None, shared.sd_model, emb_name)
loaded_networks.clear()
@@ -244,7 +289,7 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No if net is None:
failed_to_load_networks.append(name)
- print(f"Couldn't find network with name {name}")
+ logging.info(f"Couldn't find network with name {name}")
continue
net.te_multiplier = te_multipliers[i] if te_multipliers else 1.0
@@ -252,26 +297,54 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No net.dyn_dim = dyn_dims[i] if dyn_dims else 1.0
loaded_networks.append(net)
+ for emb_name, embedding in net.bundle_embeddings.items():
+ if embedding.loaded is None and emb_name in emb_db.word_embeddings:
+ logger.warning(
+ f'Skip bundle embedding: "{emb_name}"'
+ ' as it was already loaded from embeddings folder'
+ )
+ continue
+
+ embedding.loaded = False
+ if emb_db.expected_shape == -1 or emb_db.expected_shape == embedding.shape:
+ embedding.loaded = True
+ emb_db.register_embedding(embedding, shared.sd_model)
+ else:
+ emb_db.skipped_embeddings[name] = embedding
+
if failed_to_load_networks:
- sd_hijack.model_hijack.comments.append("Failed to find networks: " + ", ".join(failed_to_load_networks))
+ sd_hijack.model_hijack.comments.append("Networks not found: " + ", ".join(failed_to_load_networks))
purge_networks_from_memory()
-def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
+def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
weights_backup = getattr(self, "network_weights_backup", None)
+ bias_backup = getattr(self, "network_bias_backup", None)
- if weights_backup is None:
+ if weights_backup is None and bias_backup is None:
return
- if isinstance(self, torch.nn.MultiheadAttention):
- self.in_proj_weight.copy_(weights_backup[0])
- self.out_proj.weight.copy_(weights_backup[1])
+ if weights_backup is not None:
+ if isinstance(self, torch.nn.MultiheadAttention):
+ self.in_proj_weight.copy_(weights_backup[0])
+ self.out_proj.weight.copy_(weights_backup[1])
+ else:
+ self.weight.copy_(weights_backup)
+
+ if bias_backup is not None:
+ if isinstance(self, torch.nn.MultiheadAttention):
+ self.out_proj.bias.copy_(bias_backup)
+ else:
+ self.bias.copy_(bias_backup)
else:
- self.weight.copy_(weights_backup)
+ if isinstance(self, torch.nn.MultiheadAttention):
+ self.out_proj.bias = None
+ else:
+ self.bias = None
-def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
+def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
"""
Applies the currently selected set of networks to the weights of torch layer self.
If weights already have this particular set of networks applied, does nothing.
@@ -286,7 +359,10 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn wanted_names = tuple((x.name, x.te_multiplier, x.unet_multiplier, x.dyn_dim) for x in loaded_networks)
weights_backup = getattr(self, "network_weights_backup", None)
- if weights_backup is None:
+ if weights_backup is None and wanted_names != ():
+ if current_names != ():
+ raise RuntimeError("no backup weights found and current weights are not unchanged")
+
if isinstance(self, torch.nn.MultiheadAttention):
weights_backup = (self.in_proj_weight.to(devices.cpu, copy=True), self.out_proj.weight.to(devices.cpu, copy=True))
else:
@@ -294,21 +370,41 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn self.network_weights_backup = weights_backup
+ bias_backup = getattr(self, "network_bias_backup", None)
+ if bias_backup is None:
+ if isinstance(self, torch.nn.MultiheadAttention) and self.out_proj.bias is not None:
+ bias_backup = self.out_proj.bias.to(devices.cpu, copy=True)
+ elif getattr(self, 'bias', None) is not None:
+ bias_backup = self.bias.to(devices.cpu, copy=True)
+ else:
+ bias_backup = None
+ self.network_bias_backup = bias_backup
+
if current_names != wanted_names:
network_restore_weights_from_backup(self)
for net in loaded_networks:
module = net.modules.get(network_layer_name, None)
if module is not None and hasattr(self, 'weight'):
- with torch.no_grad():
- updown = module.calc_updown(self.weight)
-
- if len(self.weight.shape) == 4 and self.weight.shape[1] == 9:
- # inpainting model. zero pad updown to make channel[1] 4 to 9
- updown = torch.nn.functional.pad(updown, (0, 0, 0, 0, 0, 5))
+ try:
+ with torch.no_grad():
+ updown, ex_bias = module.calc_updown(self.weight)
+
+ if len(self.weight.shape) == 4 and self.weight.shape[1] == 9:
+ # inpainting model. zero pad updown to make channel[1] 4 to 9
+ updown = torch.nn.functional.pad(updown, (0, 0, 0, 0, 0, 5))
+
+ self.weight += updown
+ if ex_bias is not None and hasattr(self, 'bias'):
+ if self.bias is None:
+ self.bias = torch.nn.Parameter(ex_bias)
+ else:
+ self.bias += ex_bias
+ except RuntimeError as e:
+ logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
+ extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
- self.weight += updown
- continue
+ continue
module_q = net.modules.get(network_layer_name + "_q_proj", None)
module_k = net.modules.get(network_layer_name + "_k_proj", None)
@@ -316,21 +412,33 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn module_out = net.modules.get(network_layer_name + "_out_proj", None)
if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
- with torch.no_grad():
- updown_q = module_q.calc_updown(self.in_proj_weight)
- updown_k = module_k.calc_updown(self.in_proj_weight)
- updown_v = module_v.calc_updown(self.in_proj_weight)
- updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
- updown_out = module_out.calc_updown(self.out_proj.weight)
-
- self.in_proj_weight += updown_qkv
- self.out_proj.weight += updown_out
- continue
+ try:
+ with torch.no_grad():
+ updown_q, _ = module_q.calc_updown(self.in_proj_weight)
+ updown_k, _ = module_k.calc_updown(self.in_proj_weight)
+ updown_v, _ = module_v.calc_updown(self.in_proj_weight)
+ updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
+ updown_out, ex_bias = module_out.calc_updown(self.out_proj.weight)
+
+ self.in_proj_weight += updown_qkv
+ self.out_proj.weight += updown_out
+ if ex_bias is not None:
+ if self.out_proj.bias is None:
+ self.out_proj.bias = torch.nn.Parameter(ex_bias)
+ else:
+ self.out_proj.bias += ex_bias
+
+ except RuntimeError as e:
+ logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
+ extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
+
+ continue
if module is None:
continue
- print(f'failed to calculate network weights for layer {network_layer_name}')
+ logging.debug(f"Network {net.name} layer {network_layer_name}: couldn't find supported operation")
+ extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
self.network_current_names = wanted_names
@@ -357,7 +465,7 @@ def network_forward(module, input, original_forward): if module is None:
continue
- y = module.forward(y, input)
+ y = module.forward(input, y)
return y
@@ -365,48 +473,79 @@ def network_forward(module, input, original_forward): def network_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]):
self.network_current_names = ()
self.network_weights_backup = None
+ self.network_bias_backup = None
def network_Linear_forward(self, input):
if shared.opts.lora_functional:
- return network_forward(self, input, torch.nn.Linear_forward_before_network)
+ return network_forward(self, input, originals.Linear_forward)
network_apply_weights(self)
- return torch.nn.Linear_forward_before_network(self, input)
+ return originals.Linear_forward(self, input)
def network_Linear_load_state_dict(self, *args, **kwargs):
network_reset_cached_weight(self)
- return torch.nn.Linear_load_state_dict_before_network(self, *args, **kwargs)
+ return originals.Linear_load_state_dict(self, *args, **kwargs)
def network_Conv2d_forward(self, input):
if shared.opts.lora_functional:
- return network_forward(self, input, torch.nn.Conv2d_forward_before_network)
+ return network_forward(self, input, originals.Conv2d_forward)
network_apply_weights(self)
- return torch.nn.Conv2d_forward_before_network(self, input)
+ return originals.Conv2d_forward(self, input)
def network_Conv2d_load_state_dict(self, *args, **kwargs):
network_reset_cached_weight(self)
- return torch.nn.Conv2d_load_state_dict_before_network(self, *args, **kwargs)
+ return originals.Conv2d_load_state_dict(self, *args, **kwargs)
+
+
+def network_GroupNorm_forward(self, input):
+ if shared.opts.lora_functional:
+ return network_forward(self, input, originals.GroupNorm_forward)
+
+ network_apply_weights(self)
+
+ return originals.GroupNorm_forward(self, input)
+
+
+def network_GroupNorm_load_state_dict(self, *args, **kwargs):
+ network_reset_cached_weight(self)
+
+ return originals.GroupNorm_load_state_dict(self, *args, **kwargs)
+
+
+def network_LayerNorm_forward(self, input):
+ if shared.opts.lora_functional:
+ return network_forward(self, input, originals.LayerNorm_forward)
+
+ network_apply_weights(self)
+
+ return originals.LayerNorm_forward(self, input)
+
+
+def network_LayerNorm_load_state_dict(self, *args, **kwargs):
+ network_reset_cached_weight(self)
+
+ return originals.LayerNorm_load_state_dict(self, *args, **kwargs)
def network_MultiheadAttention_forward(self, *args, **kwargs):
network_apply_weights(self)
- return torch.nn.MultiheadAttention_forward_before_network(self, *args, **kwargs)
+ return originals.MultiheadAttention_forward(self, *args, **kwargs)
def network_MultiheadAttention_load_state_dict(self, *args, **kwargs):
network_reset_cached_weight(self)
- return torch.nn.MultiheadAttention_load_state_dict_before_network(self, *args, **kwargs)
+ return originals.MultiheadAttention_load_state_dict(self, *args, **kwargs)
def list_available_networks():
@@ -474,9 +613,14 @@ def infotext_pasted(infotext, params): params["Prompt"] += "\n" + "".join(added)
+originals: lora_patches.LoraPatches = None
+
+extra_network_lora = None
+
available_networks = {}
available_network_aliases = {}
loaded_networks = []
+loaded_bundle_embeddings = {}
networks_in_memory = {}
available_network_hash_lookup = {}
forbidden_network_aliases = {}
diff --git a/extensions-builtin/Lora/scripts/lora_script.py b/extensions-builtin/Lora/scripts/lora_script.py index 6ab8b6e7..ef23968c 100644 --- a/extensions-builtin/Lora/scripts/lora_script.py +++ b/extensions-builtin/Lora/scripts/lora_script.py @@ -1,57 +1,30 @@ import re
-import torch
import gradio as gr
from fastapi import FastAPI
import network
import networks
import lora # noqa:F401
+import lora_patches
import extra_networks_lora
import ui_extra_networks_lora
from modules import script_callbacks, ui_extra_networks, extra_networks, shared
+
def unload():
- torch.nn.Linear.forward = torch.nn.Linear_forward_before_network
- torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_network
- torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_network
- torch.nn.Conv2d._load_from_state_dict = torch.nn.Conv2d_load_state_dict_before_network
- torch.nn.MultiheadAttention.forward = torch.nn.MultiheadAttention_forward_before_network
- torch.nn.MultiheadAttention._load_from_state_dict = torch.nn.MultiheadAttention_load_state_dict_before_network
+ networks.originals.undo()
def before_ui():
ui_extra_networks.register_page(ui_extra_networks_lora.ExtraNetworksPageLora())
- extra_network = extra_networks_lora.ExtraNetworkLora()
- extra_networks.register_extra_network(extra_network)
- extra_networks.register_extra_network_alias(extra_network, "lyco")
-
-
-if not hasattr(torch.nn, 'Linear_forward_before_network'):
- torch.nn.Linear_forward_before_network = torch.nn.Linear.forward
-
-if not hasattr(torch.nn, 'Linear_load_state_dict_before_network'):
- torch.nn.Linear_load_state_dict_before_network = torch.nn.Linear._load_from_state_dict
-
-if not hasattr(torch.nn, 'Conv2d_forward_before_network'):
- torch.nn.Conv2d_forward_before_network = torch.nn.Conv2d.forward
-
-if not hasattr(torch.nn, 'Conv2d_load_state_dict_before_network'):
- torch.nn.Conv2d_load_state_dict_before_network = torch.nn.Conv2d._load_from_state_dict
-
-if not hasattr(torch.nn, 'MultiheadAttention_forward_before_network'):
- torch.nn.MultiheadAttention_forward_before_network = torch.nn.MultiheadAttention.forward
+ networks.extra_network_lora = extra_networks_lora.ExtraNetworkLora()
+ extra_networks.register_extra_network(networks.extra_network_lora)
+ extra_networks.register_extra_network_alias(networks.extra_network_lora, "lyco")
-if not hasattr(torch.nn, 'MultiheadAttention_load_state_dict_before_network'):
- torch.nn.MultiheadAttention_load_state_dict_before_network = torch.nn.MultiheadAttention._load_from_state_dict
-torch.nn.Linear.forward = networks.network_Linear_forward
-torch.nn.Linear._load_from_state_dict = networks.network_Linear_load_state_dict
-torch.nn.Conv2d.forward = networks.network_Conv2d_forward
-torch.nn.Conv2d._load_from_state_dict = networks.network_Conv2d_load_state_dict
-torch.nn.MultiheadAttention.forward = networks.network_MultiheadAttention_forward
-torch.nn.MultiheadAttention._load_from_state_dict = networks.network_MultiheadAttention_load_state_dict
+networks.originals = lora_patches.LoraPatches()
script_callbacks.on_model_loaded(networks.assign_network_names_to_compvis_modules)
script_callbacks.on_script_unloaded(unload)
diff --git a/extensions-builtin/Lora/ui_edit_user_metadata.py b/extensions-builtin/Lora/ui_edit_user_metadata.py index 390d9dde..c7011909 100644 --- a/extensions-builtin/Lora/ui_edit_user_metadata.py +++ b/extensions-builtin/Lora/ui_edit_user_metadata.py @@ -70,6 +70,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) metadata = item.get("metadata") or {}
keys = {
+ 'ss_output_name': "Output name:",
'ss_sd_model_name': "Model:",
'ss_clip_skip': "Clip skip:",
'ss_network_module': "Kohya module:",
diff --git a/extensions-builtin/Lora/ui_extra_networks_lora.py b/extensions-builtin/Lora/ui_extra_networks_lora.py index 3629e5c0..df02c663 100644 --- a/extensions-builtin/Lora/ui_extra_networks_lora.py +++ b/extensions-builtin/Lora/ui_extra_networks_lora.py @@ -17,6 +17,8 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): def create_item(self, name, index=None, enable_filter=True):
lora_on_disk = networks.available_networks.get(name)
+ if lora_on_disk is None:
+ return
path, ext = os.path.splitext(lora_on_disk.filename)
@@ -25,9 +27,10 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): item = {
"name": name,
"filename": lora_on_disk.filename,
+ "shorthash": lora_on_disk.shorthash,
"preview": self.find_preview(path),
"description": self.find_description(path),
- "search_term": self.search_terms_from_path(lora_on_disk.filename),
+ "search_term": self.search_terms_from_path(lora_on_disk.filename) + " " + (lora_on_disk.hash or ""),
"local_preview": f"{path}.{shared.opts.samples_format}",
"metadata": lora_on_disk.metadata,
"sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
@@ -65,9 +68,10 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): return item
def list_items(self):
- for index, name in enumerate(networks.available_networks):
+ # instantiate a list to protect against concurrent modification
+ names = list(networks.available_networks)
+ for index, name in enumerate(names):
item = self.create_item(name, index)
-
if item is not None:
yield item
diff --git a/extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js b/extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js index e7616b98..45c7600a 100644 --- a/extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js +++ b/extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js @@ -12,8 +12,22 @@ onUiLoaded(async() => { "Sketch": elementIDs.sketch }; + // Helper functions // Get active tab + + /** + * Waits for an element to be present in the DOM. + */ + const waitForElement = (id) => new Promise(resolve => { + const checkForElement = () => { + const element = document.querySelector(id); + if (element) return resolve(element); + setTimeout(checkForElement, 100); + }; + checkForElement(); + }); + function getActiveTab(elements, all = false) { const tabs = elements.img2imgTabs.querySelectorAll("button"); @@ -34,7 +48,7 @@ onUiLoaded(async() => { // Wait until opts loaded async function waitForOpts() { - for (;;) { + for (; ;) { if (window.opts && Object.keys(window.opts).length) { return window.opts; } @@ -255,7 +269,7 @@ onUiLoaded(async() => { input?.addEventListener("input", () => restoreImgRedMask(elements)); } - function applyZoomAndPan(elemId) { + function applyZoomAndPan(elemId, isExtension = true) { const targetElement = gradioApp().querySelector(elemId); if (!targetElement) { @@ -367,6 +381,12 @@ onUiLoaded(async() => { panY: 0 }; + if (isExtension) { + targetElement.style.overflow = "hidden"; + } + + targetElement.isZoomed = false; + fixCanvas(); targetElement.style.transform = `scale(${elemData[elemId].zoomLevel}) translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px)`; @@ -377,8 +397,27 @@ onUiLoaded(async() => { toggleOverlap("off"); fullScreenMode = false; + const closeBtn = targetElement.querySelector("button[aria-label='Remove Image']"); + if (closeBtn) { + closeBtn.addEventListener("click", resetZoom); + } + + if (canvas && isExtension) { + const parentElement = targetElement.closest('[id^="component-"]'); + if ( + canvas && + parseFloat(canvas.style.width) > parentElement.offsetWidth && + parseFloat(targetElement.style.width) > parentElement.offsetWidth + ) { + fitToElement(); + return; + } + + } + if ( canvas && + !isExtension && parseFloat(canvas.style.width) > 865 && parseFloat(targetElement.style.width) > 865 ) { @@ -387,9 +426,6 @@ onUiLoaded(async() => { } targetElement.style.width = ""; - if (canvas) { - targetElement.style.height = canvas.style.height; - } } // Toggle the zIndex of the target element between two values, allowing it to overlap or be overlapped by other elements @@ -445,7 +481,7 @@ onUiLoaded(async() => { // Update the zoom level and pan position of the target element based on the values of the zoomLevel, panX and panY variables function updateZoom(newZoomLevel, mouseX, mouseY) { - newZoomLevel = Math.max(0.5, Math.min(newZoomLevel, 15)); + newZoomLevel = Math.max(0.1, Math.min(newZoomLevel, 15)); elemData[elemId].panX += mouseX - (mouseX * newZoomLevel) / elemData[elemId].zoomLevel; @@ -456,6 +492,10 @@ onUiLoaded(async() => { targetElement.style.transform = `translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px) scale(${newZoomLevel})`; toggleOverlap("on"); + if (isExtension) { + targetElement.style.overflow = "visible"; + } + return newZoomLevel; } @@ -478,10 +518,12 @@ onUiLoaded(async() => { fullScreenMode = false; elemData[elemId].zoomLevel = updateZoom( elemData[elemId].zoomLevel + - (operation === "+" ? delta : -delta), + (operation === "+" ? delta : -delta), zoomPosX - targetElement.getBoundingClientRect().left, zoomPosY - targetElement.getBoundingClientRect().top ); + + targetElement.isZoomed = true; } } @@ -495,10 +537,19 @@ onUiLoaded(async() => { //Reset Zoom targetElement.style.transform = `translate(${0}px, ${0}px) scale(${1})`; + let parentElement; + + if (isExtension) { + parentElement = targetElement.closest('[id^="component-"]'); + } else { + parentElement = targetElement.parentElement; + } + + // Get element and screen dimensions const elementWidth = targetElement.offsetWidth; const elementHeight = targetElement.offsetHeight; - const parentElement = targetElement.parentElement; + const screenWidth = parentElement.clientWidth; const screenHeight = parentElement.clientHeight; @@ -551,8 +602,12 @@ onUiLoaded(async() => { if (!canvas) return; - if (canvas.offsetWidth > 862) { - targetElement.style.width = canvas.offsetWidth + "px"; + if (canvas.offsetWidth > 862 || isExtension) { + targetElement.style.width = (canvas.offsetWidth + 2) + "px"; + } + + if (isExtension) { + targetElement.style.overflow = "visible"; } if (fullScreenMode) { @@ -657,17 +712,18 @@ onUiLoaded(async() => { // Simulation of the function to put a long image into the screen. // We detect if an image has a scroll bar or not, make a fullscreen to reveal the image, then reduce it to fit into the element. // We hide the image and show it to the user when it is ready. - function autoExpand(e) { - const canvas = document.querySelector(`${elemId} canvas[key="interface"]`); - const isMainTab = activeElement === elementIDs.inpaint || activeElement === elementIDs.inpaintSketch || activeElement === elementIDs.sketch; - if (canvas && isMainTab) { - if (hasHorizontalScrollbar(targetElement)) { + targetElement.isExpanded = false; + function autoExpand() { + const canvas = document.querySelector(`${elemId} canvas[key="interface"]`); + if (canvas) { + if (hasHorizontalScrollbar(targetElement) && targetElement.isExpanded === false) { targetElement.style.visibility = "hidden"; setTimeout(() => { fitToScreen(); resetZoom(); targetElement.style.visibility = "visible"; + targetElement.isExpanded = true; }, 10); } } @@ -675,9 +731,24 @@ onUiLoaded(async() => { targetElement.addEventListener("mousemove", getMousePosition); + //observers + // Creating an observer with a callback function to handle DOM changes + const observer = new MutationObserver((mutationsList, observer) => { + for (let mutation of mutationsList) { + // If the style attribute of the canvas has changed, by observation it happens only when the picture changes + if (mutation.type === 'attributes' && mutation.attributeName === 'style' && + mutation.target.tagName.toLowerCase() === 'canvas') { + targetElement.isExpanded = false; + setTimeout(resetZoom, 10); + } + } + }); + // Apply auto expand if enabled if (hotkeysConfig.canvas_auto_expand) { targetElement.addEventListener("mousemove", autoExpand); + // Set up an observer to track attribute changes + observer.observe(targetElement, {attributes: true, childList: true, subtree: true}); } // Handle events only inside the targetElement @@ -784,6 +855,11 @@ onUiLoaded(async() => { if (isMoving && elemId === activeElement) { updatePanPosition(e.movementX, e.movementY); targetElement.style.pointerEvents = "none"; + + if (isExtension) { + targetElement.style.overflow = "visible"; + } + } else { targetElement.style.pointerEvents = "auto"; } @@ -794,13 +870,93 @@ onUiLoaded(async() => { isMoving = false; }; + // Checks for extension + function checkForOutBox() { + const parentElement = targetElement.closest('[id^="component-"]'); + if (parentElement.offsetWidth < targetElement.offsetWidth && !targetElement.isExpanded) { + resetZoom(); + targetElement.isExpanded = true; + } + + if (parentElement.offsetWidth < targetElement.offsetWidth && elemData[elemId].zoomLevel == 1) { + resetZoom(); + } + + if (parentElement.offsetWidth < targetElement.offsetWidth && targetElement.offsetWidth * elemData[elemId].zoomLevel > parentElement.offsetWidth && elemData[elemId].zoomLevel < 1 && !targetElement.isZoomed) { + resetZoom(); + } + } + + if (isExtension) { + targetElement.addEventListener("mousemove", checkForOutBox); + } + + + window.addEventListener('resize', (e) => { + resetZoom(); + + if (isExtension) { + targetElement.isExpanded = false; + targetElement.isZoomed = false; + } + }); + gradioApp().addEventListener("mousemove", handleMoveByKey); + + } - applyZoomAndPan(elementIDs.sketch); - applyZoomAndPan(elementIDs.inpaint); - applyZoomAndPan(elementIDs.inpaintSketch); + applyZoomAndPan(elementIDs.sketch, false); + applyZoomAndPan(elementIDs.inpaint, false); + applyZoomAndPan(elementIDs.inpaintSketch, false); // Make the function global so that other extensions can take advantage of this solution - window.applyZoomAndPan = applyZoomAndPan; + const applyZoomAndPanIntegration = async(id, elementIDs) => { + const mainEl = document.querySelector(id); + if (id.toLocaleLowerCase() === "none") { + for (const elementID of elementIDs) { + const el = await waitForElement(elementID); + if (!el) break; + applyZoomAndPan(elementID); + } + return; + } + + if (!mainEl) return; + mainEl.addEventListener("click", async() => { + for (const elementID of elementIDs) { + const el = await waitForElement(elementID); + if (!el) break; + applyZoomAndPan(elementID); + } + }, {once: true}); + }; + + window.applyZoomAndPan = applyZoomAndPan; // Only 1 elements, argument elementID, for example applyZoomAndPan("#txt2img_controlnet_ControlNet_input_image") + + window.applyZoomAndPanIntegration = applyZoomAndPanIntegration; // for any extension + + /* + The function `applyZoomAndPanIntegration` takes two arguments: + + 1. `id`: A string identifier for the element to which zoom and pan functionality will be applied on click. + If the `id` value is "none", the functionality will be applied to all elements specified in the second argument without a click event. + + 2. `elementIDs`: An array of string identifiers for elements. Zoom and pan functionality will be applied to each of these elements on click of the element specified by the first argument. + If "none" is specified in the first argument, the functionality will be applied to each of these elements without a click event. + + Example usage: + applyZoomAndPanIntegration("#txt2img_controlnet", ["#txt2img_controlnet_ControlNet_input_image"]); + In this example, zoom and pan functionality will be applied to the element with the identifier "txt2img_controlnet_ControlNet_input_image" upon clicking the element with the identifier "txt2img_controlnet". + */ + + // More examples + // Add integration with ControlNet txt2img One TAB + // applyZoomAndPanIntegration("#txt2img_controlnet", ["#txt2img_controlnet_ControlNet_input_image"]); + + // Add integration with ControlNet txt2img Tabs + // applyZoomAndPanIntegration("#txt2img_controlnet",Array.from({ length: 10 }, (_, i) => `#txt2img_controlnet_ControlNet-${i}_input_image`)); + + // Add integration with Inpaint Anything + // applyZoomAndPanIntegration("None", ["#ia_sam_image", "#ia_sel_mask"]); }); diff --git a/extensions-builtin/canvas-zoom-and-pan/style.css b/extensions-builtin/canvas-zoom-and-pan/style.css index 6bcc9570..5d8054e6 100644 --- a/extensions-builtin/canvas-zoom-and-pan/style.css +++ b/extensions-builtin/canvas-zoom-and-pan/style.css @@ -61,3 +61,6 @@ to {opacity: 1;} } +.styler { + overflow:inherit !important; +}
\ No newline at end of file diff --git a/extensions-builtin/extra-options-section/scripts/extra_options_section.py b/extensions-builtin/extra-options-section/scripts/extra_options_section.py index 588b64d2..983f87ff 100644 --- a/extensions-builtin/extra-options-section/scripts/extra_options_section.py +++ b/extensions-builtin/extra-options-section/scripts/extra_options_section.py @@ -22,22 +22,23 @@ class ExtraOptionsSection(scripts.Script): self.comps = []
self.setting_names = []
self.infotext_fields = []
+ extra_options = shared.opts.extra_options_img2img if is_img2img else shared.opts.extra_options_txt2img
mapping = {k: v for v, k in generation_parameters_copypaste.infotext_to_setting_name_mapping}
with gr.Blocks() as interface:
- with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and shared.opts.extra_options else gr.Group():
+ with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and extra_options else gr.Group():
- row_count = math.ceil(len(shared.opts.extra_options) / shared.opts.extra_options_cols)
+ row_count = math.ceil(len(extra_options) / shared.opts.extra_options_cols)
for row in range(row_count):
with gr.Row():
for col in range(shared.opts.extra_options_cols):
index = row * shared.opts.extra_options_cols + col
- if index >= len(shared.opts.extra_options):
+ if index >= len(extra_options):
break
- setting_name = shared.opts.extra_options[index]
+ setting_name = extra_options[index]
with FormColumn():
comp = ui_settings.create_setting_component(setting_name)
@@ -64,7 +65,8 @@ class ExtraOptionsSection(scripts.Script): shared.options_templates.update(shared.options_section(('ui', "User interface"), {
- "extra_options": shared.OptionInfo([], "Options in main UI", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img/img2img interfaces").needs_reload_ui(),
+ "extra_options_txt2img": shared.OptionInfo([], "Options in main UI - txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
+ "extra_options_img2img": shared.OptionInfo([], "Options in main UI - img2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in img2img interfaces").needs_reload_ui(),
"extra_options_cols": shared.OptionInfo(1, "Options in main UI - number of columns", gr.Number, {"precision": 0}).needs_reload_ui(),
"extra_options_accordion": shared.OptionInfo(False, "Options in main UI - place into an accordion").needs_reload_ui()
}))
diff --git a/extensions-builtin/hypertile/hypertile.py b/extensions-builtin/hypertile/hypertile.py new file mode 100644 index 00000000..a40c1311 --- /dev/null +++ b/extensions-builtin/hypertile/hypertile.py @@ -0,0 +1,348 @@ +""" +Hypertile module for splitting attention layers in SD-1.5 U-Net and SD-1.5 VAE +Warn: The patch works well only if the input image has a width and height that are multiples of 128 +Original author: @tfernd Github: https://github.com/tfernd/HyperTile +""" + +from __future__ import annotations + +import functools +from dataclasses import dataclass +from typing import Callable +from typing_extensions import Literal + +import logging +from functools import wraps, cache +from contextlib import contextmanager + +import math +import torch.nn as nn +import random + +from einops import rearrange + + +@dataclass +class HypertileParams: + depth = 0 + layer_name = "" + tile_size: int = 0 + swap_size: int = 0 + aspect_ratio: float = 1.0 + forward = None + enabled = False + + + +# TODO add SD-XL layers +DEPTH_LAYERS = { + 0: [ + # SD 1.5 U-Net (diffusers) + "down_blocks.0.attentions.0.transformer_blocks.0.attn1", + "down_blocks.0.attentions.1.transformer_blocks.0.attn1", + "up_blocks.3.attentions.0.transformer_blocks.0.attn1", + "up_blocks.3.attentions.1.transformer_blocks.0.attn1", + "up_blocks.3.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.1.1.transformer_blocks.0.attn1", + "input_blocks.2.1.transformer_blocks.0.attn1", + "output_blocks.9.1.transformer_blocks.0.attn1", + "output_blocks.10.1.transformer_blocks.0.attn1", + "output_blocks.11.1.transformer_blocks.0.attn1", + # SD 1.5 VAE + "decoder.mid_block.attentions.0", + "decoder.mid.attn_1", + ], + 1: [ + # SD 1.5 U-Net (diffusers) + "down_blocks.1.attentions.0.transformer_blocks.0.attn1", + "down_blocks.1.attentions.1.transformer_blocks.0.attn1", + "up_blocks.2.attentions.0.transformer_blocks.0.attn1", + "up_blocks.2.attentions.1.transformer_blocks.0.attn1", + "up_blocks.2.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.4.1.transformer_blocks.0.attn1", + "input_blocks.5.1.transformer_blocks.0.attn1", + "output_blocks.6.1.transformer_blocks.0.attn1", + "output_blocks.7.1.transformer_blocks.0.attn1", + "output_blocks.8.1.transformer_blocks.0.attn1", + ], + 2: [ + # SD 1.5 U-Net (diffusers) + "down_blocks.2.attentions.0.transformer_blocks.0.attn1", + "down_blocks.2.attentions.1.transformer_blocks.0.attn1", + "up_blocks.1.attentions.0.transformer_blocks.0.attn1", + "up_blocks.1.attentions.1.transformer_blocks.0.attn1", + "up_blocks.1.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.7.1.transformer_blocks.0.attn1", + "input_blocks.8.1.transformer_blocks.0.attn1", + "output_blocks.3.1.transformer_blocks.0.attn1", + "output_blocks.4.1.transformer_blocks.0.attn1", + "output_blocks.5.1.transformer_blocks.0.attn1", + ], + 3: [ + # SD 1.5 U-Net (diffusers) + "mid_block.attentions.0.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "middle_block.1.transformer_blocks.0.attn1", + ], +} +# XL layers, thanks for GitHub@gel-crabs for the help +DEPTH_LAYERS_XL = { + 0: [ + # SD 1.5 U-Net (diffusers) + "down_blocks.0.attentions.0.transformer_blocks.0.attn1", + "down_blocks.0.attentions.1.transformer_blocks.0.attn1", + "up_blocks.3.attentions.0.transformer_blocks.0.attn1", + "up_blocks.3.attentions.1.transformer_blocks.0.attn1", + "up_blocks.3.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.4.1.transformer_blocks.0.attn1", + "input_blocks.5.1.transformer_blocks.0.attn1", + "output_blocks.3.1.transformer_blocks.0.attn1", + "output_blocks.4.1.transformer_blocks.0.attn1", + "output_blocks.5.1.transformer_blocks.0.attn1", + # SD 1.5 VAE + "decoder.mid_block.attentions.0", + "decoder.mid.attn_1", + ], + 1: [ + # SD 1.5 U-Net (diffusers) + #"down_blocks.1.attentions.0.transformer_blocks.0.attn1", + #"down_blocks.1.attentions.1.transformer_blocks.0.attn1", + #"up_blocks.2.attentions.0.transformer_blocks.0.attn1", + #"up_blocks.2.attentions.1.transformer_blocks.0.attn1", + #"up_blocks.2.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.4.1.transformer_blocks.1.attn1", + "input_blocks.5.1.transformer_blocks.1.attn1", + "output_blocks.3.1.transformer_blocks.1.attn1", + "output_blocks.4.1.transformer_blocks.1.attn1", + "output_blocks.5.1.transformer_blocks.1.attn1", + "input_blocks.7.1.transformer_blocks.0.attn1", + "input_blocks.8.1.transformer_blocks.0.attn1", + "output_blocks.0.1.transformer_blocks.0.attn1", + "output_blocks.1.1.transformer_blocks.0.attn1", + "output_blocks.2.1.transformer_blocks.0.attn1", + "input_blocks.7.1.transformer_blocks.1.attn1", + "input_blocks.8.1.transformer_blocks.1.attn1", + "output_blocks.0.1.transformer_blocks.1.attn1", + "output_blocks.1.1.transformer_blocks.1.attn1", + "output_blocks.2.1.transformer_blocks.1.attn1", + "input_blocks.7.1.transformer_blocks.2.attn1", + "input_blocks.8.1.transformer_blocks.2.attn1", + "output_blocks.0.1.transformer_blocks.2.attn1", + "output_blocks.1.1.transformer_blocks.2.attn1", + "output_blocks.2.1.transformer_blocks.2.attn1", + "input_blocks.7.1.transformer_blocks.3.attn1", + "input_blocks.8.1.transformer_blocks.3.attn1", + "output_blocks.0.1.transformer_blocks.3.attn1", + "output_blocks.1.1.transformer_blocks.3.attn1", + "output_blocks.2.1.transformer_blocks.3.attn1", + "input_blocks.7.1.transformer_blocks.4.attn1", + "input_blocks.8.1.transformer_blocks.4.attn1", + "output_blocks.0.1.transformer_blocks.4.attn1", + "output_blocks.1.1.transformer_blocks.4.attn1", + "output_blocks.2.1.transformer_blocks.4.attn1", + "input_blocks.7.1.transformer_blocks.5.attn1", + "input_blocks.8.1.transformer_blocks.5.attn1", + "output_blocks.0.1.transformer_blocks.5.attn1", + "output_blocks.1.1.transformer_blocks.5.attn1", + "output_blocks.2.1.transformer_blocks.5.attn1", + "input_blocks.7.1.transformer_blocks.6.attn1", + "input_blocks.8.1.transformer_blocks.6.attn1", + "output_blocks.0.1.transformer_blocks.6.attn1", + "output_blocks.1.1.transformer_blocks.6.attn1", + "output_blocks.2.1.transformer_blocks.6.attn1", + "input_blocks.7.1.transformer_blocks.7.attn1", + "input_blocks.8.1.transformer_blocks.7.attn1", + "output_blocks.0.1.transformer_blocks.7.attn1", + "output_blocks.1.1.transformer_blocks.7.attn1", + "output_blocks.2.1.transformer_blocks.7.attn1", + "input_blocks.7.1.transformer_blocks.8.attn1", + "input_blocks.8.1.transformer_blocks.8.attn1", + "output_blocks.0.1.transformer_blocks.8.attn1", + "output_blocks.1.1.transformer_blocks.8.attn1", + "output_blocks.2.1.transformer_blocks.8.attn1", + "input_blocks.7.1.transformer_blocks.9.attn1", + "input_blocks.8.1.transformer_blocks.9.attn1", + "output_blocks.0.1.transformer_blocks.9.attn1", + "output_blocks.1.1.transformer_blocks.9.attn1", + "output_blocks.2.1.transformer_blocks.9.attn1", + ], + 2: [ + # SD 1.5 U-Net (diffusers) + "mid_block.attentions.0.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "middle_block.1.transformer_blocks.0.attn1", + "middle_block.1.transformer_blocks.1.attn1", + "middle_block.1.transformer_blocks.2.attn1", + "middle_block.1.transformer_blocks.3.attn1", + "middle_block.1.transformer_blocks.4.attn1", + "middle_block.1.transformer_blocks.5.attn1", + "middle_block.1.transformer_blocks.6.attn1", + "middle_block.1.transformer_blocks.7.attn1", + "middle_block.1.transformer_blocks.8.attn1", + "middle_block.1.transformer_blocks.9.attn1", + ], + 3 : [] # TODO - separate layers for SD-XL +} + + +RNG_INSTANCE = random.Random() + + +def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int: + """ + Returns a random divisor of value that + x * min_value <= value + if max_options is 1, the behavior is deterministic + """ + min_value = min(min_value, value) + + # All big divisors of value (inclusive) + divisors = [i for i in range(min_value, value + 1) if value % i == 0] # divisors in small -> big order + + ns = [value // i for i in divisors[:max_options]] # has at least 1 element # big -> small order + + idx = RNG_INSTANCE.randint(0, len(ns) - 1) + + return ns[idx] + + +def set_hypertile_seed(seed: int) -> None: + RNG_INSTANCE.seed(seed) + + +@functools.cache +def largest_tile_size_available(width: int, height: int) -> int: + """ + Calculates the largest tile size available for a given width and height + Tile size is always a power of 2 + """ + gcd = math.gcd(width, height) + largest_tile_size_available = 1 + while gcd % (largest_tile_size_available * 2) == 0: + largest_tile_size_available *= 2 + return largest_tile_size_available + + +def iterative_closest_divisors(hw:int, aspect_ratio:float) -> tuple[int, int]: + """ + Finds h and w such that h*w = hw and h/w = aspect_ratio + We check all possible divisors of hw and return the closest to the aspect ratio + """ + divisors = [i for i in range(2, hw + 1) if hw % i == 0] # all divisors of hw + pairs = [(i, hw // i) for i in divisors] # all pairs of divisors of hw + ratios = [w/h for h, w in pairs] # all ratios of pairs of divisors of hw + closest_ratio = min(ratios, key=lambda x: abs(x - aspect_ratio)) # closest ratio to aspect_ratio + closest_pair = pairs[ratios.index(closest_ratio)] # closest pair of divisors to aspect_ratio + return closest_pair + + +@cache +def find_hw_candidates(hw:int, aspect_ratio:float) -> tuple[int, int]: + """ + Finds h and w such that h*w = hw and h/w = aspect_ratio + """ + h, w = round(math.sqrt(hw * aspect_ratio)), round(math.sqrt(hw / aspect_ratio)) + # find h and w such that h*w = hw and h/w = aspect_ratio + if h * w != hw: + w_candidate = hw / h + # check if w is an integer + if not w_candidate.is_integer(): + h_candidate = hw / w + # check if h is an integer + if not h_candidate.is_integer(): + return iterative_closest_divisors(hw, aspect_ratio) + else: + h = int(h_candidate) + else: + w = int(w_candidate) + return h, w + + +def self_attn_forward(params: HypertileParams, scale_depth=True) -> Callable: + + @wraps(params.forward) + def wrapper(*args, **kwargs): + if not params.enabled: + return params.forward(*args, **kwargs) + + latent_tile_size = max(128, params.tile_size) // 8 + x = args[0] + + # VAE + if x.ndim == 4: + b, c, h, w = x.shape + + nh = random_divisor(h, latent_tile_size, params.swap_size) + nw = random_divisor(w, latent_tile_size, params.swap_size) + + if nh * nw > 1: + x = rearrange(x, "b c (nh h) (nw w) -> (b nh nw) c h w", nh=nh, nw=nw) # split into nh * nw tiles + + out = params.forward(x, *args[1:], **kwargs) + + if nh * nw > 1: + out = rearrange(out, "(b nh nw) c h w -> b c (nh h) (nw w)", nh=nh, nw=nw) + + # U-Net + else: + hw: int = x.size(1) + h, w = find_hw_candidates(hw, params.aspect_ratio) + assert h * w == hw, f"Invalid aspect ratio {params.aspect_ratio} for input of shape {x.shape}, hw={hw}, h={h}, w={w}" + + factor = 2 ** params.depth if scale_depth else 1 + nh = random_divisor(h, latent_tile_size * factor, params.swap_size) + nw = random_divisor(w, latent_tile_size * factor, params.swap_size) + + if nh * nw > 1: + x = rearrange(x, "b (nh h nw w) c -> (b nh nw) (h w) c", h=h // nh, w=w // nw, nh=nh, nw=nw) + + out = params.forward(x, *args[1:], **kwargs) + + if nh * nw > 1: + out = rearrange(out, "(b nh nw) hw c -> b nh nw hw c", nh=nh, nw=nw) + out = rearrange(out, "b nh nw (h w) c -> b (nh h nw w) c", h=h // nh, w=w // nw) + + return out + + return wrapper + + +def hypertile_hook_model(model: nn.Module, width, height, *, enable=False, tile_size_max=128, swap_size=1, max_depth=3, is_sdxl=False): + hypertile_layers = getattr(model, "__webui_hypertile_layers", None) + if hypertile_layers is None: + if not enable: + return + + hypertile_layers = {} + layers = DEPTH_LAYERS_XL if is_sdxl else DEPTH_LAYERS + + for depth in range(4): + for layer_name, module in model.named_modules(): + if any(layer_name.endswith(try_name) for try_name in layers[depth]): + params = HypertileParams() + module.__webui_hypertile_params = params + params.forward = module.forward + params.depth = depth + params.layer_name = layer_name + module.forward = self_attn_forward(params) + + hypertile_layers[layer_name] = 1 + + model.__webui_hypertile_layers = hypertile_layers + + aspect_ratio = width / height + tile_size = min(largest_tile_size_available(width, height), tile_size_max) + + for layer_name, module in model.named_modules(): + if layer_name in hypertile_layers: + params = module.__webui_hypertile_params + + params.tile_size = tile_size + params.swap_size = swap_size + params.aspect_ratio = aspect_ratio + params.enabled = enable and params.depth <= max_depth diff --git a/extensions-builtin/hypertile/scripts/hypertile_script.py b/extensions-builtin/hypertile/scripts/hypertile_script.py new file mode 100644 index 00000000..3cc29cd1 --- /dev/null +++ b/extensions-builtin/hypertile/scripts/hypertile_script.py @@ -0,0 +1,73 @@ +import hypertile
+from modules import scripts, script_callbacks, shared
+
+
+class ScriptHypertile(scripts.Script):
+ name = "Hypertile"
+
+ def title(self):
+ return self.name
+
+ def show(self, is_img2img):
+ return scripts.AlwaysVisible
+
+ def process(self, p, *args):
+ hypertile.set_hypertile_seed(p.all_seeds[0])
+
+ configure_hypertile(p.width, p.height, enable_unet=shared.opts.hypertile_enable_unet)
+
+ def before_hr(self, p, *args):
+ configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=shared.opts.hypertile_enable_unet_secondpass or shared.opts.hypertile_enable_unet)
+
+
+def configure_hypertile(width, height, enable_unet=True):
+ hypertile.hypertile_hook_model(
+ shared.sd_model.first_stage_model,
+ width,
+ height,
+ swap_size=shared.opts.hypertile_swap_size_vae,
+ max_depth=shared.opts.hypertile_max_depth_vae,
+ tile_size_max=shared.opts.hypertile_max_tile_vae,
+ enable=shared.opts.hypertile_enable_vae,
+ )
+
+ hypertile.hypertile_hook_model(
+ shared.sd_model.model,
+ width,
+ height,
+ swap_size=shared.opts.hypertile_swap_size_unet,
+ max_depth=shared.opts.hypertile_max_depth_unet,
+ tile_size_max=shared.opts.hypertile_max_tile_unet,
+ enable=enable_unet,
+ is_sdxl=shared.sd_model.is_sdxl
+ )
+
+
+def on_ui_settings():
+ import gradio as gr
+
+ options = {
+ "hypertile_explanation": shared.OptionHTML("""
+ <a href='https://github.com/tfernd/HyperTile'>Hypertile</a> optimizes the self-attention layer within U-Net and VAE models,
+ resulting in a reduction in computation time ranging from 1 to 4 times. The larger the generated image is, the greater the
+ benefit.
+ """),
+
+ "hypertile_enable_unet": shared.OptionInfo(False, "Enable Hypertile U-Net").info("noticeable change in details of the generated picture; if enabled, overrides the setting below"),
+ "hypertile_enable_unet_secondpass": shared.OptionInfo(False, "Enable Hypertile U-Net for hires fix second pass"),
+ "hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}),
+ "hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
+ "hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-net swap size", gr.Slider, {"minimum": 0, "maximum": 6, "step": 1}),
+
+ "hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE").info("minimal change in the generated picture"),
+ "hypertile_max_depth_vae": shared.OptionInfo(3, "Hypertile VAE max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}),
+ "hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
+ "hypertile_swap_size_vae": shared.OptionInfo(3, "Hypertile VAE swap size ", gr.Slider, {"minimum": 0, "maximum": 6, "step": 1}),
+ }
+
+ for name, opt in options.items():
+ opt.section = ('hypertile', "Hypertile")
+ shared.opts.add_option(name, opt)
+
+
+script_callbacks.on_ui_settings(on_ui_settings)
diff --git a/extensions-builtin/mobile/javascript/mobile.js b/extensions-builtin/mobile/javascript/mobile.js index 12cae4b7..bff1aced 100644 --- a/extensions-builtin/mobile/javascript/mobile.js +++ b/extensions-builtin/mobile/javascript/mobile.js @@ -12,6 +12,8 @@ function isMobile() { } function reportWindowSize() { + if (gradioApp().querySelector('.toprow-compact-tools')) return; // not applicable for compact prompt layout + var currentlyMobile = isMobile(); if (currentlyMobile == isSetupForMobile) return; isSetupForMobile = currentlyMobile; @@ -20,7 +22,13 @@ function reportWindowSize() { var button = gradioApp().getElementById(tab + '_generate_box'); var target = gradioApp().getElementById(currentlyMobile ? tab + '_results' : tab + '_actions_column'); target.insertBefore(button, target.firstElementChild); + + gradioApp().getElementById(tab + '_results').classList.toggle('mobile', currentlyMobile); } } window.addEventListener("resize", reportWindowSize); + +onUiLoaded(function() { + reportWindowSize(); +}); diff --git a/javascript/dragdrop.js b/javascript/dragdrop.js index 5803daea..d680daf5 100644 --- a/javascript/dragdrop.js +++ b/javascript/dragdrop.js @@ -119,7 +119,7 @@ window.addEventListener('paste', e => { } const firstFreeImageField = visibleImageFields - .filter(el => el.querySelector('input[type=file]'))?.[0]; + .filter(el => !el.querySelector('img'))?.[0]; dropReplaceImage( firstFreeImageField ? diff --git a/javascript/edit-attention.js b/javascript/edit-attention.js index 8906c892..688c2f11 100644 --- a/javascript/edit-attention.js +++ b/javascript/edit-attention.js @@ -18,37 +18,43 @@ function keyupEditAttention(event) { const before = text.substring(0, selectionStart); let beforeParen = before.lastIndexOf(OPEN); if (beforeParen == -1) return false; - let beforeParenClose = before.lastIndexOf(CLOSE); - while (beforeParenClose !== -1 && beforeParenClose > beforeParen) { - beforeParen = before.lastIndexOf(OPEN, beforeParen - 1); - beforeParenClose = before.lastIndexOf(CLOSE, beforeParenClose - 1); - } + + let beforeClosingParen = before.lastIndexOf(CLOSE); + if (beforeClosingParen != -1 && beforeClosingParen > beforeParen) return false; // Find closing parenthesis around current cursor const after = text.substring(selectionStart); let afterParen = after.indexOf(CLOSE); if (afterParen == -1) return false; - let afterParenOpen = after.indexOf(OPEN); - while (afterParenOpen !== -1 && afterParen > afterParenOpen) { - afterParen = after.indexOf(CLOSE, afterParen + 1); - afterParenOpen = after.indexOf(OPEN, afterParenOpen + 1); - } - if (beforeParen === -1 || afterParen === -1) return false; + + let afterOpeningParen = after.indexOf(OPEN); + if (afterOpeningParen != -1 && afterOpeningParen < afterParen) return false; // Set the selection to the text between the parenthesis const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen); - const lastColon = parenContent.lastIndexOf(":"); - selectionStart = beforeParen + 1; - selectionEnd = selectionStart + lastColon; + if (/.*:-?[\d.]+/s.test(parenContent)) { + const lastColon = parenContent.lastIndexOf(":"); + selectionStart = beforeParen + 1; + selectionEnd = selectionStart + lastColon; + } else { + selectionStart = beforeParen + 1; + selectionEnd = selectionStart + parenContent.length; + } + target.setSelectionRange(selectionStart, selectionEnd); return true; } function selectCurrentWord() { if (selectionStart !== selectionEnd) return false; - const delimiters = opts.keyedit_delimiters + " \r\n\t"; + const whitespace_delimiters = {"Tab": "\t", "Carriage Return": "\r", "Line Feed": "\n"}; + let delimiters = opts.keyedit_delimiters; + + for (let i of opts.keyedit_delimiters_whitespace) { + delimiters += whitespace_delimiters[i]; + } - // seek backward until to find beggining + // seek backward to find beginning while (!delimiters.includes(text[selectionStart - 1]) && selectionStart > 0) { selectionStart--; } @@ -63,7 +69,7 @@ function keyupEditAttention(event) { } // If the user hasn't selected anything, let's select their current parenthesis block or word - if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')')) { + if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')') && !selectCurrentParenthesisBlock('[', ']')) { selectCurrentWord(); } @@ -71,33 +77,54 @@ function keyupEditAttention(event) { var closeCharacter = ')'; var delta = opts.keyedit_precision_attention; + var start = selectionStart > 0 ? text[selectionStart - 1] : ""; + var end = text[selectionEnd]; - if (selectionStart > 0 && text[selectionStart - 1] == '<') { + if (start == '<') { closeCharacter = '>'; delta = opts.keyedit_precision_extra; - } else if (selectionStart == 0 || text[selectionStart - 1] != "(") { + } else if (start == '(' && end == ')' || start == '[' && end == ']') { // convert old-style (((emphasis))) + let numParen = 0; + + while (text[selectionStart - numParen - 1] == start && text[selectionEnd + numParen] == end) { + numParen++; + } + if (start == "[") { + weight = (1 / 1.1) ** numParen; + } else { + weight = 1.1 ** numParen; + } + + weight = Math.round(weight / opts.keyedit_precision_attention) * opts.keyedit_precision_attention; + + text = text.slice(0, selectionStart - numParen) + "(" + text.slice(selectionStart, selectionEnd) + ":" + weight + ")" + text.slice(selectionEnd + numParen); + selectionStart -= numParen - 1; + selectionEnd -= numParen - 1; + } else if (start != '(') { // do not include spaces at the end while (selectionEnd > selectionStart && text[selectionEnd - 1] == ' ') { - selectionEnd -= 1; + selectionEnd--; } + if (selectionStart == selectionEnd) { return; } text = text.slice(0, selectionStart) + "(" + text.slice(selectionStart, selectionEnd) + ":1.0)" + text.slice(selectionEnd); - selectionStart += 1; - selectionEnd += 1; + selectionStart++; + selectionEnd++; } - var end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1; - var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + 1 + end)); + if (text[selectionEnd] != ':') return; + var weightLength = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1; + var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + weightLength)); if (isNaN(weight)) return; weight += isPlus ? delta : -delta; weight = parseFloat(weight.toPrecision(12)); - if (String(weight).length == 1) weight += ".0"; + if (Number.isInteger(weight)) weight += ".0"; if (closeCharacter == ')' && weight == 1) { var endParenPos = text.substring(selectionEnd).indexOf(')'); @@ -105,7 +132,7 @@ function keyupEditAttention(event) { selectionStart--; selectionEnd--; } else { - text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + end); + text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + weightLength); } target.focus(); diff --git a/javascript/extensions.js b/javascript/extensions.js index 1f7254c5..312131b7 100644 --- a/javascript/extensions.js +++ b/javascript/extensions.js @@ -33,7 +33,7 @@ function extensions_check() { var id = randomId(); - requestProgress(id, gradioApp().getElementById('extensions_installed_top'), null, function() { + requestProgress(id, gradioApp().getElementById('extensions_installed_html'), null, function() { }); diff --git a/javascript/extraNetworks.js b/javascript/extraNetworks.js index 897ebeba..a1bf29a8 100644 --- a/javascript/extraNetworks.js +++ b/javascript/extraNetworks.js @@ -26,8 +26,9 @@ function setupExtraNetworksForTab(tabname) { var refresh = gradioApp().getElementById(tabname + '_extra_refresh'); var showDirsDiv = gradioApp().getElementById(tabname + '_extra_show_dirs'); var showDirs = gradioApp().querySelector('#' + tabname + '_extra_show_dirs input'); + var promptContainer = gradioApp().querySelector('.prompt-container-compact#' + tabname + '_prompt_container'); + var negativePrompt = gradioApp().querySelector('#' + tabname + '_neg_prompt'); - sort.dataset.sortkey = 'sortDefault'; tabs.appendChild(searchDiv); tabs.appendChild(sort); tabs.appendChild(sortOrder); @@ -49,20 +50,23 @@ function setupExtraNetworksForTab(tabname) { elem.style.display = visible ? "" : "none"; }); + + applySort(); }; var applySort = function() { + var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card'); + var reverse = sortOrder.classList.contains("sortReverse"); - var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim(); - sortKey = sortKey ? "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1) : ""; - var sortKeyStore = sortKey ? sortKey + (reverse ? "Reverse" : "") : ""; - if (!sortKey || sortKeyStore == sort.dataset.sortkey) { + var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim() || "name"; + sortKey = "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1); + var sortKeyStore = sortKey + "-" + (reverse ? "Descending" : "Ascending") + "-" + cards.length; + + if (sortKeyStore == sort.dataset.sortkey) { return; } - sort.dataset.sortkey = sortKeyStore; - var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card'); cards.forEach(function(card) { card.originalParentElement = card.parentElement; }); @@ -88,15 +92,13 @@ function setupExtraNetworksForTab(tabname) { }; search.addEventListener("input", applyFilter); - applyFilter(); - ["change", "blur", "click"].forEach(function(evt) { - sort.querySelector("input").addEventListener(evt, applySort); - }); sortOrder.addEventListener("click", function() { sortOrder.classList.toggle("sortReverse"); applySort(); }); + applyFilter(); + extraNetworksApplySort[tabname] = applySort; extraNetworksApplyFilter[tabname] = applyFilter; var showDirsUpdate = function() { @@ -109,11 +111,47 @@ function setupExtraNetworksForTab(tabname) { showDirsUpdate(); } +function extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt) { + if (!gradioApp().querySelector('.toprow-compact-tools')) return; // only applicable for compact prompt layout + + var promptContainer = gradioApp().getElementById(tabname + '_prompt_container'); + var prompt = gradioApp().getElementById(tabname + '_prompt_row'); + var negPrompt = gradioApp().getElementById(tabname + '_neg_prompt_row'); + var elem = id ? gradioApp().getElementById(id) : null; + + if (showNegativePrompt && elem) { + elem.insertBefore(negPrompt, elem.firstChild); + } else { + promptContainer.insertBefore(negPrompt, promptContainer.firstChild); + } + + if (showPrompt && elem) { + elem.insertBefore(prompt, elem.firstChild); + } else { + promptContainer.insertBefore(prompt, promptContainer.firstChild); + } +} + + +function extraNetworksUrelatedTabSelected(tabname) { // called from python when user selects an unrelated tab (generate) + extraNetworksMovePromptToTab(tabname, '', false, false); +} + +function extraNetworksTabSelected(tabname, id, showPrompt, showNegativePrompt) { // called from python when user selects an extra networks tab + extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt); + +} + function applyExtraNetworkFilter(tabname) { setTimeout(extraNetworksApplyFilter[tabname], 1); } +function applyExtraNetworkSort(tabname) { + setTimeout(extraNetworksApplySort[tabname], 1); +} + var extraNetworksApplyFilter = {}; +var extraNetworksApplySort = {}; var activePromptTextarea = {}; function setupExtraNetworks() { @@ -140,14 +178,15 @@ function setupExtraNetworks() { onUiLoaded(setupExtraNetworks); -var re_extranet = /<([^:]+:[^:]+):[\d.]+>(.*)/; -var re_extranet_g = /\s+<([^:]+:[^:]+):[\d.]+>/g; +var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/; +var re_extranet_g = /<([^:^>]+:[^:]+):[\d.]+>/g; function tryToRemoveExtraNetworkFromPrompt(textarea, text) { var m = text.match(re_extranet); var replaced = false; var newTextareaText; if (m) { + var extraTextBeforeNet = opts.extra_networks_add_text_separator; var extraTextAfterNet = m[2]; var partToSearch = m[1]; var foundAtPosition = -1; @@ -161,8 +200,13 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) { return found; }); - if (foundAtPosition >= 0 && newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) { - newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length); + if (foundAtPosition >= 0) { + if (newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) { + newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length); + } + if (newTextareaText.substr(foundAtPosition - extraTextBeforeNet.length, extraTextBeforeNet.length) == extraTextBeforeNet) { + newTextareaText = newTextareaText.substr(0, foundAtPosition - extraTextBeforeNet.length) + newTextareaText.substr(foundAtPosition); + } } } else { newTextareaText = textarea.value.replaceAll(new RegExp(text, "g"), function(found) { @@ -216,27 +260,24 @@ function extraNetworksSearchButton(tabs_id, event) { var globalPopup = null; var globalPopupInner = null; + function closePopup() { if (!globalPopup) return; - globalPopup.style.display = "none"; } + function popup(contents) { if (!globalPopup) { globalPopup = document.createElement('div'); - globalPopup.onclick = closePopup; globalPopup.classList.add('global-popup'); var close = document.createElement('div'); close.classList.add('global-popup-close'); - close.onclick = closePopup; + close.addEventListener("click", closePopup); close.title = "Close"; globalPopup.appendChild(close); globalPopupInner = document.createElement('div'); - globalPopupInner.onclick = function(event) { - event.stopPropagation(); return false; - }; globalPopupInner.classList.add('global-popup-inner'); globalPopup.appendChild(globalPopupInner); @@ -249,6 +290,15 @@ function popup(contents) { globalPopup.style.display = "flex"; } +var storedPopupIds = {}; +function popupId(id) { + if (!storedPopupIds[id]) { + storedPopupIds[id] = gradioApp().getElementById(id); + } + + popup(storedPopupIds[id]); +} + function extraNetworksShowMetadata(text) { var elem = document.createElement('pre'); elem.classList.add('popup-metadata'); @@ -326,13 +376,13 @@ function extraNetworksEditUserMetadata(event, tabname, extraPage, cardName) { function extraNetworksRefreshSingleCard(page, tabname, name) { requestGet("./sd_extra_networks/get-single-card", {page: page, tabname: tabname, name: name}, function(data) { if (data && data.html) { - var card = gradioApp().querySelector('.card[data-name=' + JSON.stringify(name) + ']'); // likely using the wrong stringify function + var card = gradioApp().querySelector(`#${tabname}_${page.replace(" ", "_")}_cards > .card[data-name="${name}"]`); var newDiv = document.createElement('DIV'); newDiv.innerHTML = data.html; var newCard = newDiv.firstElementChild; - newCard.style = ''; + newCard.style.display = ''; card.parentElement.insertBefore(newCard, card); card.parentElement.removeChild(card); } diff --git a/javascript/imageviewer.js b/javascript/imageviewer.js index c21d396e..e4dae91b 100644 --- a/javascript/imageviewer.js +++ b/javascript/imageviewer.js @@ -33,8 +33,11 @@ function updateOnBackgroundChange() { const modalImage = gradioApp().getElementById("modalImage"); if (modalImage && modalImage.offsetParent) { let currentButton = selected_gallery_button(); - - if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) { + let preview = gradioApp().querySelectorAll('.livePreview > img'); + if (preview.length > 0) { + // show preview image if available + modalImage.src = preview[preview.length - 1].src; + } else if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) { modalImage.src = currentButton.children[0].src; if (modalImage.style.display === 'none') { const modal = gradioApp().getElementById("lightboxModal"); diff --git a/javascript/inputAccordion.js b/javascript/inputAccordion.js index f2839852..7570309a 100644 --- a/javascript/inputAccordion.js +++ b/javascript/inputAccordion.js @@ -1,37 +1,68 @@ -var observerAccordionOpen = new MutationObserver(function(mutations) { - mutations.forEach(function(mutationRecord) { - var elem = mutationRecord.target; - var open = elem.classList.contains('open'); +function inputAccordionChecked(id, checked) { + var accordion = gradioApp().getElementById(id); + accordion.visibleCheckbox.checked = checked; + accordion.onVisibleCheckboxChange(); +} - var accordion = elem.parentNode; - accordion.classList.toggle('input-accordion-open', open); +function setupAccordion(accordion) { + var labelWrap = accordion.querySelector('.label-wrap'); + var gradioCheckbox = gradioApp().querySelector('#' + accordion.id + "-checkbox input"); + var extra = gradioApp().querySelector('#' + accordion.id + "-extra"); + var span = labelWrap.querySelector('span'); + var linked = true; - var checkbox = gradioApp().querySelector('#' + accordion.id + "-checkbox input"); - checkbox.checked = open; - updateInput(checkbox); + var isOpen = function() { + return labelWrap.classList.contains('open'); + }; - var extra = gradioApp().querySelector('#' + accordion.id + "-extra"); - if (extra) { - extra.style.display = open ? "" : "none"; - } + var observerAccordionOpen = new MutationObserver(function(mutations) { + mutations.forEach(function(mutationRecord) { + accordion.classList.toggle('input-accordion-open', isOpen()); + + if (linked) { + accordion.visibleCheckbox.checked = isOpen(); + accordion.onVisibleCheckboxChange(); + } + }); }); -}); + observerAccordionOpen.observe(labelWrap, {attributes: true, attributeFilter: ['class']}); -function inputAccordionChecked(id, checked) { - var label = gradioApp().querySelector('#' + id + " .label-wrap"); - if (label.classList.contains('open') != checked) { - label.click(); + if (extra) { + labelWrap.insertBefore(extra, labelWrap.lastElementChild); } + + accordion.onChecked = function(checked) { + if (isOpen() != checked) { + labelWrap.click(); + } + }; + + var visibleCheckbox = document.createElement('INPUT'); + visibleCheckbox.type = 'checkbox'; + visibleCheckbox.checked = isOpen(); + visibleCheckbox.id = accordion.id + "-visible-checkbox"; + visibleCheckbox.className = gradioCheckbox.className + " input-accordion-checkbox"; + span.insertBefore(visibleCheckbox, span.firstChild); + + accordion.visibleCheckbox = visibleCheckbox; + accordion.onVisibleCheckboxChange = function() { + if (linked && isOpen() != visibleCheckbox.checked) { + labelWrap.click(); + } + + gradioCheckbox.checked = visibleCheckbox.checked; + updateInput(gradioCheckbox); + }; + + visibleCheckbox.addEventListener('click', function(event) { + linked = false; + event.stopPropagation(); + }); + visibleCheckbox.addEventListener('input', accordion.onVisibleCheckboxChange); } onUiLoaded(function() { for (var accordion of gradioApp().querySelectorAll('.input-accordion')) { - var labelWrap = accordion.querySelector('.label-wrap'); - observerAccordionOpen.observe(labelWrap, {attributes: true, attributeFilter: ['class']}); - - var extra = gradioApp().querySelector('#' + accordion.id + "-extra"); - if (extra) { - labelWrap.insertBefore(extra, labelWrap.lastElementChild); - } + setupAccordion(accordion); } }); diff --git a/javascript/localization.js b/javascript/localization.js index 0c9032f9..8f00c186 100644 --- a/javascript/localization.js +++ b/javascript/localization.js @@ -107,12 +107,41 @@ function processNode(node) { }); } +function localizeWholePage() { + processNode(gradioApp()); + + function elem(comp) { + var elem_id = comp.props.elem_id ? comp.props.elem_id : "component-" + comp.id; + return gradioApp().getElementById(elem_id); + } + + for (var comp of window.gradio_config.components) { + if (comp.props.webui_tooltip) { + let e = elem(comp); + + let tl = e ? getTranslation(e.title) : undefined; + if (tl !== undefined) { + e.title = tl; + } + } + if (comp.props.placeholder) { + let e = elem(comp); + let textbox = e ? e.querySelector('[placeholder]') : null; + + let tl = textbox ? getTranslation(textbox.placeholder) : undefined; + if (tl !== undefined) { + textbox.placeholder = tl; + } + } + } +} + function dumpTranslations() { if (!hasLocalization()) { // If we don't have any localization, // we will not have traversed the app to find // original_lines, so do that now. - processNode(gradioApp()); + localizeWholePage(); } var dumped = {}; if (localization.rtl) { @@ -154,7 +183,7 @@ document.addEventListener("DOMContentLoaded", function() { }); }); - processNode(gradioApp()); + localizeWholePage(); if (localization.rtl) { // if the language is from right to left, (new MutationObserver((mutations, observer) => { // wait for the style to load diff --git a/javascript/notification.js b/javascript/notification.js index 76c5715d..3ee972ae 100644 --- a/javascript/notification.js +++ b/javascript/notification.js @@ -15,7 +15,7 @@ onAfterUiUpdate(function() { } } - const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"][style*="display: block"] div[id$="_results"] .thumbnail-item > img'); + const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"] div[id$="_results"] .thumbnail-item > img'); if (galleryPreviews == null) return; @@ -26,7 +26,11 @@ onAfterUiUpdate(function() { lastHeadImg = headImg; // play notification sound if available - gradioApp().querySelector('#audio_notification audio')?.play(); + const notificationAudio = gradioApp().querySelector('#audio_notification audio'); + if (notificationAudio) { + notificationAudio.volume = opts.notification_volume / 100.0 || 1.0; + notificationAudio.play(); + } if (document.hasFocus()) return; diff --git a/javascript/progressbar.js b/javascript/progressbar.js index 29299787..77761495 100644 --- a/javascript/progressbar.js +++ b/javascript/progressbar.js @@ -69,7 +69,6 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre var dateStart = new Date(); var wasEverActive = false; var parentProgressbar = progressbarContainer.parentNode; - var parentGallery = gallery ? gallery.parentNode : null; var divProgress = document.createElement('div'); divProgress.className = 'progressDiv'; @@ -80,32 +79,26 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre divProgress.appendChild(divInner); parentProgressbar.insertBefore(divProgress, progressbarContainer); - if (parentGallery) { - var livePreview = document.createElement('div'); - livePreview.className = 'livePreview'; - parentGallery.insertBefore(livePreview, gallery); - } + var livePreview = null; var removeProgressBar = function() { + if (!divProgress) return; + setTitle(""); parentProgressbar.removeChild(divProgress); - if (parentGallery) parentGallery.removeChild(livePreview); + if (gallery && livePreview) gallery.removeChild(livePreview); atEnd(); + + divProgress = null; }; - var fun = function(id_task, id_live_preview) { - request("./internal/progress", {id_task: id_task, id_live_preview: id_live_preview}, function(res) { + var funProgress = function(id_task) { + request("./internal/progress", {id_task: id_task, live_preview: false}, function(res) { if (res.completed) { removeProgressBar(); return; } - var rect = progressbarContainer.getBoundingClientRect(); - - if (rect.width) { - divProgress.style.width = rect.width + "px"; - } - let progressText = ""; divInner.style.width = ((res.progress || 0) * 100.0) + '%'; @@ -119,7 +112,6 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre progressText += " ETA: " + formatTime(res.eta); } - setTitle(progressText); if (res.textinfo && res.textinfo.indexOf("\n") == -1) { @@ -142,16 +134,33 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre return; } + if (onProgress) { + onProgress(res); + } - if (res.live_preview && gallery) { - rect = gallery.getBoundingClientRect(); - if (rect.width) { - livePreview.style.width = rect.width + "px"; - livePreview.style.height = rect.height + "px"; - } + setTimeout(() => { + funProgress(id_task, res.id_live_preview); + }, opts.live_preview_refresh_period || 500); + }, function() { + removeProgressBar(); + }); + }; + var funLivePreview = function(id_task, id_live_preview) { + request("./internal/progress", {id_task: id_task, id_live_preview: id_live_preview}, function(res) { + if (!divProgress) { + return; + } + + if (res.live_preview && gallery) { var img = new Image(); img.onload = function() { + if (!livePreview) { + livePreview = document.createElement('div'); + livePreview.className = 'livePreview'; + gallery.insertBefore(livePreview, gallery.firstElementChild); + } + livePreview.appendChild(img); if (livePreview.childElementCount > 2) { livePreview.removeChild(livePreview.firstElementChild); @@ -160,18 +169,18 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre img.src = res.live_preview; } - - if (onProgress) { - onProgress(res); - } - setTimeout(() => { - fun(id_task, res.id_live_preview); + funLivePreview(id_task, res.id_live_preview); }, opts.live_preview_refresh_period || 500); }, function() { removeProgressBar(); }); }; - fun(id_task, 0); + funProgress(id_task, 0); + + if (gallery) { + funLivePreview(id_task, 0); + } + } diff --git a/javascript/resizeHandle.js b/javascript/resizeHandle.js new file mode 100644 index 00000000..8c5c5169 --- /dev/null +++ b/javascript/resizeHandle.js @@ -0,0 +1,141 @@ +(function() { + const GRADIO_MIN_WIDTH = 320; + const GRID_TEMPLATE_COLUMNS = '1fr 16px 1fr'; + const PAD = 16; + const DEBOUNCE_TIME = 100; + + const R = { + tracking: false, + parent: null, + parentWidth: null, + leftCol: null, + leftColStartWidth: null, + screenX: null, + }; + + let resizeTimer; + let parents = []; + + function setLeftColGridTemplate(el, width) { + el.style.gridTemplateColumns = `${width}px 16px 1fr`; + } + + function displayResizeHandle(parent) { + if (window.innerWidth < GRADIO_MIN_WIDTH * 2 + PAD * 4) { + parent.style.display = 'flex'; + if (R.handle != null) { + R.handle.style.opacity = '0'; + } + return false; + } else { + parent.style.display = 'grid'; + if (R.handle != null) { + R.handle.style.opacity = '100'; + } + return true; + } + } + + function afterResize(parent) { + if (displayResizeHandle(parent) && parent.style.gridTemplateColumns != GRID_TEMPLATE_COLUMNS) { + const oldParentWidth = R.parentWidth; + const newParentWidth = parent.offsetWidth; + const widthL = parseInt(parent.style.gridTemplateColumns.split(' ')[0]); + + const ratio = newParentWidth / oldParentWidth; + + const newWidthL = Math.max(Math.floor(ratio * widthL), GRADIO_MIN_WIDTH); + setLeftColGridTemplate(parent, newWidthL); + + R.parentWidth = newParentWidth; + } + } + + function setup(parent) { + const leftCol = parent.firstElementChild; + const rightCol = parent.lastElementChild; + + parents.push(parent); + + parent.style.display = 'grid'; + parent.style.gap = '0'; + parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS; + + const resizeHandle = document.createElement('div'); + resizeHandle.classList.add('resize-handle'); + parent.insertBefore(resizeHandle, rightCol); + + resizeHandle.addEventListener('mousedown', (evt) => { + if (evt.button !== 0) return; + + evt.preventDefault(); + evt.stopPropagation(); + + document.body.classList.add('resizing'); + + R.tracking = true; + R.parent = parent; + R.parentWidth = parent.offsetWidth; + R.handle = resizeHandle; + R.leftCol = leftCol; + R.leftColStartWidth = leftCol.offsetWidth; + R.screenX = evt.screenX; + }); + + resizeHandle.addEventListener('dblclick', (evt) => { + evt.preventDefault(); + evt.stopPropagation(); + + parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS; + }); + + afterResize(parent); + } + + window.addEventListener('mousemove', (evt) => { + if (evt.button !== 0) return; + + if (R.tracking) { + evt.preventDefault(); + evt.stopPropagation(); + + const delta = R.screenX - evt.screenX; + const leftColWidth = Math.max(Math.min(R.leftColStartWidth - delta, R.parent.offsetWidth - GRADIO_MIN_WIDTH - PAD), GRADIO_MIN_WIDTH); + setLeftColGridTemplate(R.parent, leftColWidth); + } + }); + + window.addEventListener('mouseup', (evt) => { + if (evt.button !== 0) return; + + if (R.tracking) { + evt.preventDefault(); + evt.stopPropagation(); + + R.tracking = false; + + document.body.classList.remove('resizing'); + } + }); + + + window.addEventListener('resize', () => { + clearTimeout(resizeTimer); + + resizeTimer = setTimeout(function() { + for (const parent of parents) { + afterResize(parent); + } + }, DEBOUNCE_TIME); + }); + + setupResizeHandle = setup; +})(); + +onUiLoaded(function() { + for (var elem of gradioApp().querySelectorAll('.resize-handle-row')) { + if (!elem.querySelector('.resize-handle')) { + setupResizeHandle(elem); + } + } +}); diff --git a/javascript/settings.js b/javascript/settings.js new file mode 100644 index 00000000..4e79ec00 --- /dev/null +++ b/javascript/settings.js @@ -0,0 +1,46 @@ +let settingsExcludeTabsFromShowAll = { + settings_tab_defaults: 1, + settings_tab_sysinfo: 1, + settings_tab_actions: 1, + settings_tab_licenses: 1, +}; + +function settingsShowAllTabs() { + gradioApp().querySelectorAll('#settings > div').forEach(function(elem) { + if (settingsExcludeTabsFromShowAll[elem.id]) return; + + elem.style.display = "block"; + }); +} + +function settingsShowOneTab() { + gradioApp().querySelector('#settings_show_one_page').click(); +} + +onUiLoaded(function() { + var edit = gradioApp().querySelector('#settings_search'); + var editTextarea = gradioApp().querySelector('#settings_search > label > input'); + var buttonShowAllPages = gradioApp().getElementById('settings_show_all_pages'); + var settings_tabs = gradioApp().querySelector('#settings div'); + + onEdit('settingsSearch', editTextarea, 250, function() { + var searchText = (editTextarea.value || "").trim().toLowerCase(); + + gradioApp().querySelectorAll('#settings > div[id^=settings_] div[id^=column_settings_] > *').forEach(function(elem) { + var visible = elem.textContent.trim().toLowerCase().indexOf(searchText) != -1; + elem.style.display = visible ? "" : "none"; + }); + + if (searchText != "") { + settingsShowAllTabs(); + } else { + settingsShowOneTab(); + } + }); + + settings_tabs.insertBefore(edit, settings_tabs.firstChild); + settings_tabs.appendChild(buttonShowAllPages); + + + buttonShowAllPages.addEventListener("click", settingsShowAllTabs); +}); diff --git a/javascript/token-counters.js b/javascript/token-counters.js index 9d81a723..2ecc7d91 100644 --- a/javascript/token-counters.js +++ b/javascript/token-counters.js @@ -1,10 +1,9 @@ -let promptTokenCountDebounceTime = 800; -let promptTokenCountTimeouts = {}; -var promptTokenCountUpdateFunctions = {}; +let promptTokenCountUpdateFunctions = {}; function update_txt2img_tokens(...args) { // Called from Gradio update_token_counter("txt2img_token_button"); + update_token_counter("txt2img_negative_token_button"); if (args.length == 2) { return args[0]; } @@ -14,6 +13,7 @@ function update_txt2img_tokens(...args) { function update_img2img_tokens(...args) { // Called from Gradio update_token_counter("img2img_token_button"); + update_token_counter("img2img_negative_token_button"); if (args.length == 2) { return args[0]; } @@ -21,16 +21,7 @@ function update_img2img_tokens(...args) { } function update_token_counter(button_id) { - if (opts.disable_token_counters) { - return; - } - if (promptTokenCountTimeouts[button_id]) { - clearTimeout(promptTokenCountTimeouts[button_id]); - } - promptTokenCountTimeouts[button_id] = setTimeout( - () => gradioApp().getElementById(button_id)?.click(), - promptTokenCountDebounceTime, - ); + promptTokenCountUpdateFunctions[button_id]?.(); } @@ -69,10 +60,11 @@ function setupTokenCounting(id, id_counter, id_button) { prompt.parentElement.insertBefore(counter, prompt); prompt.parentElement.style.position = "relative"; - promptTokenCountUpdateFunctions[id] = function() { - update_token_counter(id_button); - }; - textarea.addEventListener("input", promptTokenCountUpdateFunctions[id]); + var func = onEdit(id, textarea, 800, function() { + gradioApp().getElementById(id_button)?.click(); + }); + promptTokenCountUpdateFunctions[id] = func; + promptTokenCountUpdateFunctions[id_button] = func; } function setupTokenCounters() { diff --git a/javascript/ui.js b/javascript/ui.js index bade3089..2e262602 100644 --- a/javascript/ui.js +++ b/javascript/ui.js @@ -19,28 +19,11 @@ function all_gallery_buttons() { } function selected_gallery_button() { - var allCurrentButtons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery].gradio-gallery .thumbnail-item.thumbnail-small.selected'); - var visibleCurrentButton = null; - allCurrentButtons.forEach(function(elem) { - if (elem.parentElement.offsetParent) { - visibleCurrentButton = elem; - } - }); - return visibleCurrentButton; + return all_gallery_buttons().find(elem => elem.classList.contains('selected')) ?? null; } function selected_gallery_index() { - var buttons = all_gallery_buttons(); - var button = selected_gallery_button(); - - var result = -1; - buttons.forEach(function(v, i) { - if (v == button) { - result = i; - } - }); - - return result; + return all_gallery_buttons().findIndex(elem => elem.classList.contains('selected')); } function extract_image_from_gallery(gallery) { @@ -280,21 +263,6 @@ onAfterUiUpdate(function() { json_elem.parentElement.style.display = "none"; setupTokenCounters(); - - var show_all_pages = gradioApp().getElementById('settings_show_all_pages'); - var settings_tabs = gradioApp().querySelector('#settings div'); - if (show_all_pages && settings_tabs) { - settings_tabs.appendChild(show_all_pages); - show_all_pages.onclick = function() { - gradioApp().querySelectorAll('#settings > div').forEach(function(elem) { - if (elem.id == "settings_tab_licenses") { - return; - } - - elem.style.display = "block"; - }); - }; - } }); onOptionsChanged(function() { @@ -383,3 +351,20 @@ function switchWidthHeight(tabname) { updateInput(height); return []; } + + +var onEditTimers = {}; + +// calls func after afterMs milliseconds has passed since the input elem has beed enited by user +function onEdit(editId, elem, afterMs, func) { + var edited = function() { + var existingTimer = onEditTimers[editId]; + if (existingTimer) clearTimeout(existingTimer); + + onEditTimers[editId] = setTimeout(func, afterMs); + }; + + elem.addEventListener("input", edited); + + return edited; +} @@ -25,6 +25,13 @@ start = launch_utils.start def main():
+ if args.dump_sysinfo:
+ filename = launch_utils.dump_sysinfo()
+
+ print(f"Sysinfo saved as {filename}. Exiting...")
+
+ exit(0)
+
launch_utils.startup_timer.record("initial startup")
with launch_utils.startup_timer.subcategory("prepare environment"):
diff --git a/modules/api/api.py b/modules/api/api.py index 908c4514..09083874 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -4,6 +4,8 @@ import os import time import datetime import uvicorn +import ipaddress +import requests import gradio as gr from threading import Lock from io import BytesIO @@ -15,20 +17,18 @@ from fastapi.encoders import jsonable_encoder from secrets import compare_digest import modules.shared as shared -from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items +from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, generation_parameters_copypaste, sd_models from modules.api import models from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images from modules.textual_inversion.textual_inversion import create_embedding, train_embedding from modules.textual_inversion.preprocess import preprocess from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork -from PIL import PngImagePlugin,Image -from modules.sd_models import checkpoints_list, unload_model_weights, reload_model_weights, checkpoint_aliases -from modules.sd_vae import vae_dict +from PIL import PngImagePlugin, Image from modules.sd_models_config import find_checkpoint_config_near_filename from modules.realesrgan_model import get_realesrgan_models from modules import devices -from typing import Dict, List, Any +from typing import Any import piexif import piexif.helper from contextlib import closing @@ -56,7 +56,41 @@ def setUpscalers(req: dict): return reqDict +def verify_url(url): + """Returns True if the url refers to a global resource.""" + + import socket + from urllib.parse import urlparse + try: + parsed_url = urlparse(url) + domain_name = parsed_url.netloc + host = socket.gethostbyname_ex(domain_name) + for ip in host[2]: + ip_addr = ipaddress.ip_address(ip) + if not ip_addr.is_global: + return False + except Exception: + return False + + return True + + def decode_base64_to_image(encoding): + if encoding.startswith("http://") or encoding.startswith("https://"): + if not opts.api_enable_requests: + raise HTTPException(status_code=500, detail="Requests not allowed") + + if opts.api_forbid_local_requests and not verify_url(encoding): + raise HTTPException(status_code=500, detail="Request to local resource not allowed") + + headers = {'user-agent': opts.api_useragent} if opts.api_useragent else {} + response = requests.get(encoding, timeout=30, headers=headers) + try: + image = Image.open(BytesIO(response.content)) + return image + except Exception as e: + raise HTTPException(status_code=500, detail="Invalid image url") from e + if encoding.startswith("data:image/"): encoding = encoding.split(";")[1].split(",")[1] try: @@ -68,7 +102,8 @@ def decode_base64_to_image(encoding): def encode_pil_to_base64(image): with io.BytesIO() as output_bytes: - + if isinstance(image, str): + return image if opts.samples_format.lower() == 'png': use_metadata = False metadata = PngImagePlugin.PngInfo() @@ -186,15 +221,15 @@ class Api: self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=models.OptionsModel) self.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"]) self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=models.FlagsModel) - self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[models.SamplerItem]) - self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[models.UpscalerItem]) - self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=List[models.LatentUpscalerModeItem]) - self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[models.SDModelItem]) - self.add_api_route("/sdapi/v1/sd-vae", self.get_sd_vaes, methods=["GET"], response_model=List[models.SDVaeItem]) - self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[models.HypernetworkItem]) - self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[models.FaceRestorerItem]) - self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[models.RealesrganItem]) - self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[models.PromptStyleItem]) + self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=list[models.SamplerItem]) + self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=list[models.UpscalerItem]) + self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=list[models.LatentUpscalerModeItem]) + self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=list[models.SDModelItem]) + self.add_api_route("/sdapi/v1/sd-vae", self.get_sd_vaes, methods=["GET"], response_model=list[models.SDVaeItem]) + self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=list[models.HypernetworkItem]) + self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=list[models.FaceRestorerItem]) + self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=list[models.RealesrganItem]) + self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=list[models.PromptStyleItem]) self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse) self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"]) self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"]) @@ -207,7 +242,8 @@ class Api: self.add_api_route("/sdapi/v1/unload-checkpoint", self.unloadapi, methods=["POST"]) self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"]) self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=models.ScriptsList) - self.add_api_route("/sdapi/v1/script-info", self.get_script_info, methods=["GET"], response_model=List[models.ScriptInfo]) + self.add_api_route("/sdapi/v1/script-info", self.get_script_info, methods=["GET"], response_model=list[models.ScriptInfo]) + self.add_api_route("/sdapi/v1/extensions", self.get_extensions_list, methods=["GET"], response_model=list[models.ExtensionItem]) if shared.cmd_opts.api_server_stop: self.add_api_route("/sdapi/v1/server-kill", self.kill_webui, methods=["POST"]) @@ -330,6 +366,7 @@ class Api: with self.queue_lock: with closing(StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)) as p: + p.is_api = True p.scripts = script_runner p.outpath_grids = opts.outdir_txt2img_grids p.outpath_samples = opts.outdir_txt2img_samples @@ -390,6 +427,7 @@ class Api: with self.queue_lock: with closing(StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)) as p: p.init_images = [decode_base64_to_image(x) for x in init_images] + p.is_api = True p.scripts = script_runner p.outpath_grids = opts.outdir_img2img_grids p.outpath_samples = opts.outdir_img2img_samples @@ -436,9 +474,6 @@ class Api: return models.ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1]) def pnginfoapi(self, req: models.PNGInfoRequest): - if(not req.image.strip()): - return models.PNGInfoResponse(info="") - image = decode_base64_to_image(req.image.strip()) if image is None: return models.PNGInfoResponse(info="") @@ -447,9 +482,10 @@ class Api: if geninfo is None: geninfo = "" - items = {**{'parameters': geninfo}, **items} + params = generation_parameters_copypaste.parse_generation_parameters(geninfo) + script_callbacks.infotext_pasted_callback(geninfo, params) - return models.PNGInfoResponse(info=geninfo, items=items) + return models.PNGInfoResponse(info=geninfo, items=items, parameters=params) def progressapi(self, req: models.ProgressRequest = Depends()): # copy from check_progress_call of ui.py @@ -504,12 +540,12 @@ class Api: return {} def unloadapi(self): - unload_model_weights() + sd_models.unload_model_weights() return {} def reloadapi(self): - reload_model_weights() + sd_models.send_model_to_device(shared.sd_model) return {} @@ -527,13 +563,13 @@ class Api: return options - def set_config(self, req: Dict[str, Any]): + def set_config(self, req: dict[str, Any]): checkpoint_name = req.get("sd_model_checkpoint", None) - if checkpoint_name is not None and checkpoint_name not in checkpoint_aliases: + if checkpoint_name is not None and checkpoint_name not in sd_models.checkpoint_aliases: raise RuntimeError(f"model {checkpoint_name!r} not found") for k, v in req.items(): - shared.opts.set(k, v) + shared.opts.set(k, v, is_api=True) shared.opts.save(shared.config_filename) return @@ -565,10 +601,12 @@ class Api: ] def get_sd_models(self): - return [{"title": x.title, "model_name": x.model_name, "hash": x.shorthash, "sha256": x.sha256, "filename": x.filename, "config": find_checkpoint_config_near_filename(x)} for x in checkpoints_list.values()] + import modules.sd_models as sd_models + return [{"title": x.title, "model_name": x.model_name, "hash": x.shorthash, "sha256": x.sha256, "filename": x.filename, "config": find_checkpoint_config_near_filename(x)} for x in sd_models.checkpoints_list.values()] def get_sd_vaes(self): - return [{"model_name": x, "filename": vae_dict[x]} for x in vae_dict.keys()] + import modules.sd_vae as sd_vae + return [{"model_name": x, "filename": sd_vae.vae_dict[x]} for x in sd_vae.vae_dict.keys()] def get_hypernetworks(self): return [{"name": name, "path": shared.hypernetworks[name]} for name in shared.hypernetworks] @@ -731,6 +769,25 @@ class Api: cuda = {'error': f'{err}'} return models.MemoryResponse(ram=ram, cuda=cuda) + def get_extensions_list(self): + from modules import extensions + extensions.list_extensions() + ext_list = [] + for ext in extensions.extensions: + ext: extensions.Extension + ext.read_info_from_repo() + if ext.remote is not None: + ext_list.append({ + "name": ext.name, + "remote": ext.remote, + "branch": ext.branch, + "commit_hash":ext.commit_hash, + "commit_date":ext.commit_date, + "version":ext.version, + "enabled":ext.enabled + }) + return ext_list + def launch(self, server_name, port, root_path): self.app.include_router(self.router) uvicorn.run(self.app, host=server_name, port=port, timeout_keep_alive=shared.cmd_opts.timeout_keep_alive, root_path=root_path) diff --git a/modules/api/models.py b/modules/api/models.py index 800c9b93..a0d80af8 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -1,12 +1,10 @@ import inspect from pydantic import BaseModel, Field, create_model -from typing import Any, Optional -from typing_extensions import Literal +from typing import Any, Optional, Literal from inflection import underscore from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img from modules.shared import sd_upscalers, opts, parser -from typing import Dict, List API_NOT_ALLOWED = [ "self", @@ -50,10 +48,12 @@ class PydanticModelGenerator: additional_fields = None, ): def field_type_generator(k, v): - # field_type = str if not overrides.get(k) else overrides[k]["type"] - # print(k, v.annotation, v.default) field_type = v.annotation + if field_type == 'Image': + # images are sent as base64 strings via API + field_type = 'str' + return Optional[field_type] def merge_class_params(class_): @@ -63,7 +63,6 @@ class PydanticModelGenerator: parameters = {**parameters, **inspect.signature(classes.__init__).parameters} return parameters - self._model_name = model_name self._class_data = merge_class_params(class_instance) @@ -72,7 +71,7 @@ class PydanticModelGenerator: field=underscore(k), field_alias=k, field_type=field_type_generator(k, v), - field_value=v.default + field_value=None if isinstance(v.default, property) else v.default ) for (k,v) in self._class_data.items() if k not in API_NOT_ALLOWED ] @@ -129,12 +128,12 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator( ).generate_model() class TextToImageResponse(BaseModel): - images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.") + images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.") parameters: dict info: str class ImageToImageResponse(BaseModel): - images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.") + images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.") parameters: dict info: str @@ -167,17 +166,18 @@ class FileData(BaseModel): name: str = Field(title="File name") class ExtrasBatchImagesRequest(ExtrasBaseRequest): - imageList: List[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings") + imageList: list[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings") class ExtrasBatchImagesResponse(ExtraBaseResponse): - images: List[str] = Field(title="Images", description="The generated images in base64 format.") + images: list[str] = Field(title="Images", description="The generated images in base64 format.") class PNGInfoRequest(BaseModel): image: str = Field(title="Image", description="The base64 encoded PNG image") class PNGInfoResponse(BaseModel): info: str = Field(title="Image info", description="A string with the parameters used to generate the image") - items: dict = Field(title="Items", description="An object containing all the info the image had") + items: dict = Field(title="Items", description="A dictionary containing all the other fields the image had") + parameters: dict = Field(title="Parameters", description="A dictionary with parsed generation info fields") class ProgressRequest(BaseModel): skip_current_image: bool = Field(default=False, title="Skip current image", description="Skip current image serialization") @@ -231,8 +231,8 @@ FlagsModel = create_model("Flags", **flags) class SamplerItem(BaseModel): name: str = Field(title="Name") - aliases: List[str] = Field(title="Aliases") - options: Dict[str, str] = Field(title="Options") + aliases: list[str] = Field(title="Aliases") + options: dict[str, str] = Field(title="Options") class UpscalerItem(BaseModel): name: str = Field(title="Name") @@ -283,8 +283,8 @@ class EmbeddingItem(BaseModel): vectors: int = Field(title="Vectors", description="The number of vectors in the embedding") class EmbeddingsResponse(BaseModel): - loaded: Dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model") - skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)") + loaded: dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model") + skipped: dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)") class MemoryResponse(BaseModel): ram: dict = Field(title="RAM", description="System memory stats") @@ -302,11 +302,20 @@ class ScriptArg(BaseModel): minimum: Optional[Any] = Field(default=None, title="Minimum", description="Minimum allowed value for the argumentin UI") maximum: Optional[Any] = Field(default=None, title="Minimum", description="Maximum allowed value for the argumentin UI") step: Optional[Any] = Field(default=None, title="Minimum", description="Step for changing value of the argumentin UI") - choices: Optional[List[str]] = Field(default=None, title="Choices", description="Possible values for the argument") + choices: Optional[list[str]] = Field(default=None, title="Choices", description="Possible values for the argument") class ScriptInfo(BaseModel): name: str = Field(default=None, title="Name", description="Script name") is_alwayson: bool = Field(default=None, title="IsAlwayson", description="Flag specifying whether this script is an alwayson script") is_img2img: bool = Field(default=None, title="IsImg2img", description="Flag specifying whether this script is an img2img script") - args: List[ScriptArg] = Field(title="Arguments", description="List of script's arguments") + args: list[ScriptArg] = Field(title="Arguments", description="List of script's arguments") + +class ExtensionItem(BaseModel): + name: str = Field(title="Name", description="Extension name") + remote: str = Field(title="Remote", description="Extension Repository URL") + branch: str = Field(title="Branch", description="Extension Repository Branch") + commit_hash: str = Field(title="Commit Hash", description="Extension Repository Commit Hash") + version: str = Field(title="Version", description="Extension Version") + commit_date: str = Field(title="Commit Date", description="Extension Repository Commit Date") + enabled: bool = Field(title="Enabled", description="Flag specifying whether this extension is enabled") diff --git a/modules/cache.py b/modules/cache.py index a7cd3aeb..ff26a213 100644 --- a/modules/cache.py +++ b/modules/cache.py @@ -30,9 +30,12 @@ def dump_cache(): time.sleep(1)
with cache_lock:
- with open(cache_filename, "w", encoding="utf8") as file:
+ cache_filename_tmp = cache_filename + "-"
+ with open(cache_filename_tmp, "w", encoding="utf8") as file:
json.dump(cache_data, file, indent=4)
+ os.replace(cache_filename_tmp, cache_filename)
+
dump_cache_after = None
dump_cache_thread = None
diff --git a/modules/call_queue.py b/modules/call_queue.py index f2eb17d6..ddf0d573 100644 --- a/modules/call_queue.py +++ b/modules/call_queue.py @@ -1,11 +1,10 @@ from functools import wraps
import html
-import threading
import time
-from modules import shared, progress, errors, devices
+from modules import shared, progress, errors, devices, fifo_lock
-queue_lock = threading.Lock()
+queue_lock = fifo_lock.FIFOLock()
def wrap_queued_call(func):
diff --git a/modules/cmd_args.py b/modules/cmd_args.py index b0a11538..a9fb9bfa 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -16,6 +16,7 @@ parser.add_argument("--test-server", action='store_true', help="launch.py argume parser.add_argument("--log-startup", action='store_true', help="launch.py argument: print a detailed log of what's happening at startup")
parser.add_argument("--skip-prepare-environment", action='store_true', help="launch.py argument: skip all environment preparation")
parser.add_argument("--skip-install", action='store_true', help="launch.py argument: skip installation of packages")
+parser.add_argument("--dump-sysinfo", action='store_true', help="launch.py argument: dump limited sysinfo file (without information about extensions, options) to disk and quit")
parser.add_argument("--loglevel", type=str, help="log level; one of: CRITICAL, ERROR, WARNING, INFO, DEBUG", default=None)
parser.add_argument("--do-not-download-clip", action='store_true', help="do not download CLIP model even if it's not included in the checkpoint")
parser.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored")
@@ -35,9 +36,10 @@ parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_ parser.add_argument("--localizations-dir", type=str, default=os.path.join(script_path, 'localizations'), help="localizations directory")
parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui")
parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage")
+parser.add_argument("--medvram-sdxl", action='store_true', help="enable --medvram optimization just for SDXL models")
parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage")
parser.add_argument("--lowram", action='store_true', help="load stable diffusion checkpoint weights to VRAM instead of RAM")
-parser.add_argument("--always-batch-cond-uncond", action='store_true', help="disables cond/uncond batching that is enabled to save memory with --medvram or --lowvram")
+parser.add_argument("--always-batch-cond-uncond", action='store_true', help="does not do anything")
parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.")
parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
parser.add_argument("--upcast-sampling", action='store_true', help="upcast sampling. No effect with --no-half. Usually produces similar results to --no-half with better performance while using less memory.")
@@ -81,14 +83,14 @@ parser.add_argument("--gradio-auth", type=str, help='set gradio authentication l parser.add_argument("--gradio-auth-path", type=str, help='set gradio authentication file path ex. "/path/to/auth/file" same auth format as --gradio-auth', default=None)
parser.add_argument("--gradio-img2img-tool", type=str, help='does not do anything')
parser.add_argument("--gradio-inpaint-tool", type=str, help="does not do anything")
-parser.add_argument("--gradio-allowed-path", action='append', help="add path to gradio's allowed_paths, make it possible to serve files from it")
+parser.add_argument("--gradio-allowed-path", action='append', help="add path to gradio's allowed_paths, make it possible to serve files from it", default=[data_path])
parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")
parser.add_argument("--styles-file", type=str, help="filename to use for styles", default=os.path.join(data_path, 'styles.csv'))
parser.add_argument("--autolaunch", action='store_true', help="open the webui URL in the system's default browser upon launch", default=False)
parser.add_argument("--theme", type=str, help="launches the UI with light or dark theme", default=None)
parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
-parser.add_argument("--enable-console-prompts", action='store_true', help="print prompts to console when generating with txt2img and img2img", default=False)
+parser.add_argument("--enable-console-prompts", action='store_true', help="does not do anything", default=False) # Legacy compatibility, use as default value shared.opts.enable_console_prompts
parser.add_argument('--vae-path', type=str, help='Checkpoint to use as VAE; setting this argument disables all settings related to VAE', default=None)
parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
parser.add_argument("--api", action='store_true', help="use api=True to launch the API together with the webui (use --nowebui instead for only the API)")
@@ -105,13 +107,14 @@ parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, req parser.add_argument("--disable-tls-verify", action="store_false", help="When passed, enables the use of self-signed certificates.", default=None)
parser.add_argument("--server-name", type=str, help="Sets hostname of server", default=None)
parser.add_argument("--gradio-queue", action='store_true', help="does not do anything", default=True)
-parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gradio queue; causes the webpage to use http requests instead of websockets; was the defaul in earlier versions")
+parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gradio queue; causes the webpage to use http requests instead of websockets; was the default in earlier versions")
parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers")
parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False)
parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy')
-parser.add_argument('--add-stop-route', action='store_true', help='add /_stop route to stop server')
+parser.add_argument('--add-stop-route', action='store_true', help='does not do anything')
parser.add_argument('--api-server-stop', action='store_true', help='enable server stop/restart/kill via api')
parser.add_argument('--timeout-keep-alive', type=int, default=30, help='set timeout_keep_alive for uvicorn')
parser.add_argument("--disable-all-extensions", action='store_true', help="prevent all extensions from running regardless of any other settings", default=False)
-parser.add_argument("--disable-extra-extensions", action='store_true', help=" prevent all extensions except built-in from running regardless of any other settings", default=False)
+parser.add_argument("--disable-extra-extensions", action='store_true', help="prevent all extensions except built-in from running regardless of any other settings", default=False)
+parser.add_argument("--skip-load-model-at-start", action='store_true', help="if load a model at web start, only take effect when --nowebui", )
diff --git a/modules/config_states.py b/modules/config_states.py index 6f1ab53f..651793c7 100644 --- a/modules/config_states.py +++ b/modules/config_states.py @@ -4,18 +4,15 @@ Supports saving and restoring webui and extensions from a known working set of c import os import json -import time import tqdm from datetime import datetime -from collections import OrderedDict import git from modules import shared, extensions, errors from modules.paths_internal import script_path, config_states_dir - -all_config_states = OrderedDict() +all_config_states = {} def list_config_states(): @@ -28,15 +25,19 @@ def list_config_states(): for filename in os.listdir(config_states_dir): if filename.endswith(".json"): path = os.path.join(config_states_dir, filename) - with open(path, "r", encoding="utf-8") as f: - j = json.load(f) - j["filepath"] = path - config_states.append(j) + try: + with open(path, "r", encoding="utf-8") as f: + j = json.load(f) + assert "created_at" in j, '"created_at" does not exist' + j["filepath"] = path + config_states.append(j) + except Exception as e: + print(f'[ERROR]: Config states {path}, {e}') config_states = sorted(config_states, key=lambda cs: cs["created_at"], reverse=True) for cs in config_states: - timestamp = time.asctime(time.gmtime(cs["created_at"])) + timestamp = datetime.fromtimestamp(cs["created_at"]).strftime('%Y-%m-%d %H:%M:%S') name = cs.get("name", "Config") full_name = f"{name}: {timestamp}" all_config_states[full_name] = cs diff --git a/modules/devices.py b/modules/devices.py index c01f0602..1d4eb563 100644 --- a/modules/devices.py +++ b/modules/devices.py @@ -60,7 +60,8 @@ def enable_tf32(): # enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't # see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407 - if any(torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())): + device_id = (int(shared.cmd_opts.device_id) if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit() else 0) or torch.cuda.current_device() + if torch.cuda.get_device_capability(device_id) == (7, 5) and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16"): torch.backends.cudnn.benchmark = True torch.backends.cuda.matmul.allow_tf32 = True diff --git a/modules/errors.py b/modules/errors.py index ac9f1ee5..eb234a83 100644 --- a/modules/errors.py +++ b/modules/errors.py @@ -109,7 +109,7 @@ def check_versions(): expected_torch_version = "2.0.0"
expected_xformers_version = "0.0.20"
- expected_gradio_version = "3.39.0"
+ expected_gradio_version = "3.41.2"
if version.parse(torch.__version__) < version.parse(expected_torch_version):
print_error_explanation(f"""
diff --git a/modules/extensions.py b/modules/extensions.py index bf9a1878..1899cd52 100644 --- a/modules/extensions.py +++ b/modules/extensions.py @@ -1,11 +1,14 @@ +from __future__ import annotations
+
+import configparser
import os
import threading
+import re
from modules import shared, errors, cache, scripts
from modules.gitpython_hack import Repo
from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path # noqa: F401
-extensions = []
os.makedirs(extensions_dir, exist_ok=True)
@@ -19,11 +22,55 @@ def active(): return [x for x in extensions if x.enabled]
+class ExtensionMetadata:
+ filename = "metadata.ini"
+ config: configparser.ConfigParser
+ canonical_name: str
+ requires: list
+
+ def __init__(self, path, canonical_name):
+ self.config = configparser.ConfigParser()
+
+ filepath = os.path.join(path, self.filename)
+ if os.path.isfile(filepath):
+ try:
+ self.config.read(filepath)
+ except Exception:
+ errors.report(f"Error reading {self.filename} for extension {canonical_name}.", exc_info=True)
+
+ self.canonical_name = self.config.get("Extension", "Name", fallback=canonical_name)
+ self.canonical_name = canonical_name.lower().strip()
+
+ self.requires = self.get_script_requirements("Requires", "Extension")
+
+ def get_script_requirements(self, field, section, extra_section=None):
+ """reads a list of requirements from the config; field is the name of the field in the ini file,
+ like Requires or Before, and section is the name of the [section] in the ini file; additionally,
+ reads more requirements from [extra_section] if specified."""
+
+ x = self.config.get(section, field, fallback='')
+
+ if extra_section:
+ x = x + ', ' + self.config.get(extra_section, field, fallback='')
+
+ return self.parse_list(x.lower())
+
+ def parse_list(self, text):
+ """converts a line from config ("ext1 ext2, ext3 ") into a python list (["ext1", "ext2", "ext3"])"""
+
+ if not text:
+ return []
+
+ # both "," and " " are accepted as separator
+ return [x for x in re.split(r"[,\s]+", text.strip()) if x]
+
+
class Extension:
lock = threading.Lock()
cached_fields = ['remote', 'commit_date', 'branch', 'commit_hash', 'version']
+ metadata: ExtensionMetadata
- def __init__(self, name, path, enabled=True, is_builtin=False):
+ def __init__(self, name, path, enabled=True, is_builtin=False, metadata=None):
self.name = name
self.path = path
self.enabled = enabled
@@ -36,6 +83,8 @@ class Extension: self.branch = None
self.remote = None
self.have_info_from_repo = False
+ self.metadata = metadata if metadata else ExtensionMetadata(self.path, name.lower())
+ self.canonical_name = metadata.canonical_name
def to_dict(self):
return {x: getattr(self, x) for x in self.cached_fields}
@@ -56,6 +105,7 @@ class Extension: self.do_read_info_from_repo()
return self.to_dict()
+
try:
d = cache.cached_data_for_file('extensions-git', self.name, os.path.join(self.path, ".git"), read_from_repo)
self.from_dict(d)
@@ -136,9 +186,6 @@ class Extension: def list_extensions():
extensions.clear()
- if not os.path.isdir(extensions_dir):
- return
-
if shared.cmd_opts.disable_all_extensions:
print("*** \"--disable-all-extensions\" arg was used, will not load any extensions ***")
elif shared.opts.disable_all_extensions == "all":
@@ -148,18 +195,43 @@ def list_extensions(): elif shared.opts.disable_all_extensions == "extra":
print("*** \"Disable all extensions\" option was set, will only load built-in extensions ***")
- extension_paths = []
- for dirname in [extensions_dir, extensions_builtin_dir]:
+ loaded_extensions = {}
+
+ # scan through extensions directory and load metadata
+ for dirname in [extensions_builtin_dir, extensions_dir]:
if not os.path.isdir(dirname):
- return
+ continue
for extension_dirname in sorted(os.listdir(dirname)):
path = os.path.join(dirname, extension_dirname)
if not os.path.isdir(path):
continue
- extension_paths.append((extension_dirname, path, dirname == extensions_builtin_dir))
+ canonical_name = extension_dirname
+ metadata = ExtensionMetadata(path, canonical_name)
+
+ # check for duplicated canonical names
+ already_loaded_extension = loaded_extensions.get(metadata.canonical_name)
+ if already_loaded_extension is not None:
+ errors.report(f'Duplicate canonical name "{canonical_name}" found in extensions "{extension_dirname}" and "{already_loaded_extension.name}". Former will be discarded.', exc_info=False)
+ continue
+
+ is_builtin = dirname == extensions_builtin_dir
+ extension = Extension(name=extension_dirname, path=path, enabled=extension_dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin, metadata=metadata)
+ extensions.append(extension)
+ loaded_extensions[canonical_name] = extension
+
+ # check for requirements
+ for extension in extensions:
+ for req in extension.metadata.requires:
+ required_extension = loaded_extensions.get(req)
+ if required_extension is None:
+ errors.report(f'Extension "{extension.name}" requires "{req}" which is not installed.', exc_info=False)
+ continue
+
+ if not extension.enabled:
+ errors.report(f'Extension "{extension.name}" requires "{required_extension.name}" which is disabled.', exc_info=False)
+ continue
+
- for dirname, path, is_builtin in extension_paths:
- extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin)
- extensions.append(extension)
+extensions: list[Extension] = []
diff --git a/modules/extra_networks.py b/modules/extra_networks.py index fa28ac75..b9533677 100644 --- a/modules/extra_networks.py +++ b/modules/extra_networks.py @@ -1,6 +1,7 @@ import json
import os
import re
+import logging
from collections import defaultdict
from modules import errors
@@ -86,27 +87,55 @@ class ExtraNetwork: raise NotImplementedError
-def activate(p, extra_network_data):
- """call activate for extra networks in extra_network_data in specified order, then call
- activate for all remaining registered networks with an empty argument list"""
+def lookup_extra_networks(extra_network_data):
+ """returns a dict mapping ExtraNetwork objects to lists of arguments for those extra networks.
- activated = []
+ Example input:
+ {
+ 'lora': [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D58310>],
+ 'lyco': [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D58F70>],
+ 'hypernet': [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D5A800>]
+ }
+
+ Example output:
+
+ {
+ <extra_networks_lora.ExtraNetworkLora object at 0x0000020581BEECE0>: [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D58310>, <modules.extra_networks.ExtraNetworkParams object at 0x0000020690D58F70>],
+ <modules.extra_networks_hypernet.ExtraNetworkHypernet object at 0x0000020581BEEE60>: [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D5A800>]
+ }
+ """
- for extra_network_name, extra_network_args in extra_network_data.items():
+ res = {}
+
+ for extra_network_name, extra_network_args in list(extra_network_data.items()):
extra_network = extra_network_registry.get(extra_network_name, None)
+ alias = extra_network_aliases.get(extra_network_name, None)
- if extra_network is None:
- extra_network = extra_network_aliases.get(extra_network_name, None)
+ if alias is not None and extra_network is None:
+ extra_network = alias
if extra_network is None:
- print(f"Skipping unknown extra network: {extra_network_name}")
+ logging.info(f"Skipping unknown extra network: {extra_network_name}")
continue
+ res.setdefault(extra_network, []).extend(extra_network_args)
+
+ return res
+
+
+def activate(p, extra_network_data):
+ """call activate for extra networks in extra_network_data in specified order, then call
+ activate for all remaining registered networks with an empty argument list"""
+
+ activated = []
+
+ for extra_network, extra_network_args in lookup_extra_networks(extra_network_data).items():
+
try:
extra_network.activate(p, extra_network_args)
activated.append(extra_network)
except Exception as e:
- errors.display(e, f"activating extra network {extra_network_name} with arguments {extra_network_args}")
+ errors.display(e, f"activating extra network {extra_network.name} with arguments {extra_network_args}")
for extra_network_name, extra_network in extra_network_registry.items():
if extra_network in activated:
@@ -125,19 +154,16 @@ def deactivate(p, extra_network_data): """call deactivate for extra networks in extra_network_data in specified order, then call
deactivate for all remaining registered networks"""
- for extra_network_name in extra_network_data:
- extra_network = extra_network_registry.get(extra_network_name, None)
- if extra_network is None:
- continue
+ data = lookup_extra_networks(extra_network_data)
+ for extra_network in data:
try:
extra_network.deactivate(p)
except Exception as e:
- errors.display(e, f"deactivating extra network {extra_network_name}")
+ errors.display(e, f"deactivating extra network {extra_network.name}")
for extra_network_name, extra_network in extra_network_registry.items():
- args = extra_network_data.get(extra_network_name, None)
- if args is not None:
+ if extra_network in data:
continue
try:
diff --git a/modules/fifo_lock.py b/modules/fifo_lock.py new file mode 100644 index 00000000..c35b3ae2 --- /dev/null +++ b/modules/fifo_lock.py @@ -0,0 +1,37 @@ +import threading +import collections + + +# reference: https://gist.github.com/vitaliyp/6d54dd76ca2c3cdfc1149d33007dc34a +class FIFOLock(object): + def __init__(self): + self._lock = threading.Lock() + self._inner_lock = threading.Lock() + self._pending_threads = collections.deque() + + def acquire(self, blocking=True): + with self._inner_lock: + lock_acquired = self._lock.acquire(False) + if lock_acquired: + return True + elif not blocking: + return False + + release_event = threading.Event() + self._pending_threads.append(release_event) + + release_event.wait() + return self._lock.acquire() + + def release(self): + with self._inner_lock: + if self._pending_threads: + release_event = self._pending_threads.popleft() + release_event.set() + + self._lock.release() + + __enter__ = acquire + + def __exit__(self, t, v, tb): + self.release() diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index 386517ac..0a606515 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -9,7 +9,7 @@ from modules.paths import data_path from modules import shared, ui_tempdir, script_callbacks, processing
from PIL import Image
-re_param_code = r'\s*([\w ]+):\s*("(?:\\"[^,]|\\"|\\|[^\"])+"|[^,]*)(?:,|$)'
+re_param_code = r'\s*(\w[\w \-/]+):\s*("(?:\\.|[^\\"])+"|[^,]*)(?:,|$)'
re_param = re.compile(re_param_code)
re_imagesize = re.compile(r"^(\d+)x(\d+)$")
re_hypernet_hash = re.compile("\(([0-9a-f]+)\)$")
@@ -32,6 +32,7 @@ class ParamBinding: def reset():
paste_fields.clear()
+ registered_param_bindings.clear()
def quote(text):
diff --git a/modules/gfpgan_model.py b/modules/gfpgan_model.py index 8e0f13bd..01d668ec 100644 --- a/modules/gfpgan_model.py +++ b/modules/gfpgan_model.py @@ -9,6 +9,7 @@ from modules import paths, shared, devices, modelloader, errors model_dir = "GFPGAN"
user_path = None
model_path = os.path.join(paths.models_path, model_dir)
+model_file_path = None
model_url = "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth"
have_gfpgan = False
loaded_gfpgan_model = None
@@ -17,6 +18,7 @@ loaded_gfpgan_model = None def gfpgann():
global loaded_gfpgan_model
global model_path
+ global model_file_path
if loaded_gfpgan_model is not None:
loaded_gfpgan_model.gfpgan.to(devices.device_gfpgan)
return loaded_gfpgan_model
@@ -24,17 +26,24 @@ def gfpgann(): if gfpgan_constructor is None:
return None
- models = modelloader.load_models(model_path, model_url, user_path, ext_filter="GFPGAN")
+ models = modelloader.load_models(model_path, model_url, user_path, ext_filter=['.pth'])
+
if len(models) == 1 and models[0].startswith("http"):
model_file = models[0]
elif len(models) != 0:
- latest_file = max(models, key=os.path.getctime)
+ gfp_models = []
+ for item in models:
+ if 'GFPGAN' in os.path.basename(item):
+ gfp_models.append(item)
+ latest_file = max(gfp_models, key=os.path.getctime)
model_file = latest_file
else:
print("Unable to load gfpgan model!")
return None
+
if hasattr(facexlib.detection.retinaface, 'device'):
facexlib.detection.retinaface.device = devices.device_gfpgan
+ model_file_path = model_file
model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=devices.device_gfpgan)
loaded_gfpgan_model = model
@@ -77,19 +86,25 @@ def setup_model(dirname): global user_path
global have_gfpgan
global gfpgan_constructor
+ global model_file_path
+
+ facexlib_path = model_path
+
+ if dirname is not None:
+ facexlib_path = dirname
load_file_from_url_orig = gfpgan.utils.load_file_from_url
facex_load_file_from_url_orig = facexlib.detection.load_file_from_url
facex_load_file_from_url_orig2 = facexlib.parsing.load_file_from_url
def my_load_file_from_url(**kwargs):
- return load_file_from_url_orig(**dict(kwargs, model_dir=model_path))
+ return load_file_from_url_orig(**dict(kwargs, model_dir=model_file_path))
def facex_load_file_from_url(**kwargs):
- return facex_load_file_from_url_orig(**dict(kwargs, save_dir=model_path, model_dir=None))
+ return facex_load_file_from_url_orig(**dict(kwargs, save_dir=facexlib_path, model_dir=None))
def facex_load_file_from_url2(**kwargs):
- return facex_load_file_from_url_orig2(**dict(kwargs, save_dir=model_path, model_dir=None))
+ return facex_load_file_from_url_orig2(**dict(kwargs, save_dir=facexlib_path, model_dir=None))
gfpgan.utils.load_file_from_url = my_load_file_from_url
facexlib.detection.load_file_from_url = facex_load_file_from_url
diff --git a/modules/gitpython_hack.py b/modules/gitpython_hack.py index e537c1df..b55f0640 100644 --- a/modules/gitpython_hack.py +++ b/modules/gitpython_hack.py @@ -23,7 +23,7 @@ class Git(git.Git): ) return self._parse_object_header(ret) - def stream_object_data(self, ref: str) -> tuple[str, str, int, "Git.CatFileContentStream"]: + def stream_object_data(self, ref: str) -> tuple[str, str, int, Git.CatFileContentStream]: # Not really streaming, per se; this buffers the entire object in memory. # Shouldn't be a problem for our use case, since we're only using this for # object headers (commit objects). diff --git a/modules/gradio_extensons.py b/modules/gradio_extensons.py index 77c34c8b..e6b6835a 100644 --- a/modules/gradio_extensons.py +++ b/modules/gradio_extensons.py @@ -1,6 +1,7 @@ import gradio as gr
-from modules import scripts, ui_tempdir
+from modules import scripts, ui_tempdir, patches
+
def add_classes_to_gradio_component(comp):
"""
@@ -40,6 +41,8 @@ def Block_get_config(self): if webui_tooltip:
config["webui_tooltip"] = webui_tooltip
+ config.pop('example_inputs', None)
+
return config
@@ -51,12 +54,20 @@ def BlockContext_init(self, *args, **kwargs): return res
-original_IOComponent_init = gr.components.IOComponent.__init__
-original_Block_get_config = gr.blocks.Block.get_config
-original_BlockContext_init = gr.blocks.BlockContext.__init__
+def Blocks_get_config_file(self, *args, **kwargs):
+ config = original_Blocks_get_config_file(self, *args, **kwargs)
+
+ for comp_config in config["components"]:
+ if "example_inputs" in comp_config:
+ comp_config["example_inputs"] = {"serialized": []}
+
+ return config
+
+
+original_IOComponent_init = patches.patch(__name__, obj=gr.components.IOComponent, field="__init__", replacement=IOComponent_init)
+original_Block_get_config = patches.patch(__name__, obj=gr.blocks.Block, field="get_config", replacement=Block_get_config)
+original_BlockContext_init = patches.patch(__name__, obj=gr.blocks.BlockContext, field="__init__", replacement=BlockContext_init)
+original_Blocks_get_config_file = patches.patch(__name__, obj=gr.blocks.Blocks, field="get_config_file", replacement=Blocks_get_config_file)
-gr.components.IOComponent.__init__ = IOComponent_init
-gr.blocks.Block.get_config = Block_get_config
-gr.blocks.BlockContext.__init__ = BlockContext_init
ui_tempdir.install_ui_tempdir_override()
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 70f1cbd2..be3e4648 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -468,7 +468,7 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, shared.reload_hypernetworks()
-def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_hypernetwork_every, template_filename, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_hypernetwork(id_task, hypernetwork_name: str, learn_rate: float, batch_size: int, gradient_step: int, data_root: str, log_directory: str, training_width: int, training_height: int, varsize: bool, steps: int, clip_grad_mode: str, clip_grad_value: float, shuffle_tags: bool, tag_drop_out: bool, latent_sampling_method: str, use_weight: bool, create_image_every: int, save_hypernetwork_every: int, template_filename: str, preview_from_txt2img: bool, preview_prompt: str, preview_negative_prompt: str, preview_steps: int, preview_sampler_name: str, preview_cfg_scale: float, preview_seed: int, preview_width: int, preview_height: int):
from modules import images, processing
save_hypernetwork_every = save_hypernetwork_every or 0
@@ -698,7 +698,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi p.prompt = preview_prompt
p.negative_prompt = preview_negative_prompt
p.steps = preview_steps
- p.sampler_name = sd_samplers.samplers[preview_sampler_index].name
+ p.sampler_name = sd_samplers.samplers_map[preview_sampler_name.lower()]
p.cfg_scale = preview_cfg_scale
p.seed = preview_seed
p.width = preview_width
diff --git a/modules/images.py b/modules/images.py index 019c1d60..daf4eebe 100644 --- a/modules/images.py +++ b/modules/images.py @@ -355,7 +355,9 @@ class FilenameGenerator: 'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
'datetime': lambda self, *args: self.datetime(*args), # accepts formats: [datetime], [datetime<Format>], [datetime<Format><Time Zone>]
'job_timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
- 'prompt_hash': lambda self: hashlib.sha256(self.prompt.encode()).hexdigest()[0:8],
+ 'prompt_hash': lambda self, *args: self.string_hash(self.prompt, *args),
+ 'negative_prompt_hash': lambda self, *args: self.string_hash(self.p.negative_prompt, *args),
+ 'full_prompt_hash': lambda self, *args: self.string_hash(f"{self.p.prompt} {self.p.negative_prompt}", *args), # a space in between to create a unique string
'prompt': lambda self: sanitize_filename_part(self.prompt),
'prompt_no_styles': lambda self: self.prompt_no_style(),
'prompt_spaces': lambda self: sanitize_filename_part(self.prompt, replace_spaces=False),
@@ -368,7 +370,8 @@ class FilenameGenerator: 'denoising': lambda self: self.p.denoising_strength if self.p and self.p.denoising_strength else NOTHING_AND_SKIP_PREVIOUS_TEXT,
'user': lambda self: self.p.user,
'vae_filename': lambda self: self.get_vae_filename(),
- 'none': lambda self: '', # Overrides the default so you can get just the sequence number
+ 'none': lambda self: '', # Overrides the default, so you can get just the sequence number
+ 'image_hash': lambda self, *args: self.image_hash(*args) # accepts formats: [image_hash<length>] default full hash
}
default_time_format = '%Y%m%d%H%M%S'
@@ -448,6 +451,14 @@ class FilenameGenerator: return sanitize_filename_part(formatted_time, replace_spaces=False)
+ def image_hash(self, *args):
+ length = int(args[0]) if (args and args[0] != "") else None
+ return hashlib.sha256(self.image.tobytes()).hexdigest()[0:length]
+
+ def string_hash(self, text, *args):
+ length = int(args[0]) if (args and args[0] != "") else 8
+ return hashlib.sha256(text.encode()).hexdigest()[0:length]
+
def apply(self, x):
res = ''
@@ -550,6 +561,8 @@ def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_p })
piexif.insert(exif_bytes, filename)
+ elif extension.lower() == ".gif":
+ image.save(filename, format=image_format, comment=geninfo)
else:
image.save(filename, format=image_format, quality=opts.jpeg_quality)
@@ -589,6 +602,11 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i """
namegen = FilenameGenerator(p, seed, prompt, image)
+ # WebP and JPG formats have maximum dimension limits of 16383 and 65535 respectively. switch to PNG which has a much higher limit
+ if (image.height > 65535 or image.width > 65535) and extension.lower() in ("jpg", "jpeg") or (image.height > 16383 or image.width > 16383) and extension.lower() == "webp":
+ print('Image dimensions too large; saving as PNG')
+ extension = ".png"
+
if save_to_dirs is None:
save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt)
@@ -645,7 +663,13 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i save_image_with_geninfo(image_to_save, info, temp_file_path, extension, existing_pnginfo=params.pnginfo, pnginfo_section_name=pnginfo_section_name)
- os.replace(temp_file_path, filename_without_extension + extension)
+ filename = filename_without_extension + extension
+ if shared.opts.save_images_replace_action != "Replace":
+ n = 0
+ while os.path.exists(filename):
+ n += 1
+ filename = f"{filename_without_extension}-{n}{extension}"
+ os.replace(temp_file_path, filename)
fullfn_without_extension, extension = os.path.splitext(params.filename)
if hasattr(os, 'statvfs'):
@@ -702,7 +726,12 @@ def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]: geninfo = items.pop('parameters', None)
if "exif" in items:
- exif = piexif.load(items["exif"])
+ exif_data = items["exif"]
+ try:
+ exif = piexif.load(exif_data)
+ except OSError:
+ # memory / exif was not valid so piexif tried to read from a file
+ exif = None
exif_comment = (exif or {}).get("Exif", {}).get(piexif.ExifIFD.UserComment, b'')
try:
exif_comment = piexif.helper.UserComment.load(exif_comment)
@@ -712,6 +741,8 @@ def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]: if exif_comment:
items['exif comment'] = exif_comment
geninfo = exif_comment
+ elif "comment" in items: # for gif
+ geninfo = items["comment"].decode('utf8', errors="ignore")
for field in IGNORED_INFO_KEYS:
items.pop(field, None)
diff --git a/modules/img2img.py b/modules/img2img.py index c7bbbac8..c583290a 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -10,6 +10,7 @@ from modules import images as imgutil from modules.generation_parameters_copypaste import create_override_settings_dict, parse_generation_parameters
from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
from modules.shared import opts, state
+from modules.sd_models import get_closet_checkpoint_match
import modules.shared as shared
import modules.processing as processing
from modules.ui import plaintext_to_html
@@ -41,7 +42,10 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal cfg_scale = p.cfg_scale
sampler_name = p.sampler_name
steps = p.steps
-
+ override_settings = p.override_settings
+ sd_model_checkpoint_override = get_closet_checkpoint_match(override_settings.get("sd_model_checkpoint", None))
+ batch_results = None
+ discard_further_results = False
for i, image in enumerate(images):
state.job = f"{i+1} out of {len(images)}"
if state.skipped:
@@ -104,33 +108,58 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal p.sampler_name = parsed_parameters.get("Sampler", sampler_name)
p.steps = int(parsed_parameters.get("Steps", steps))
+ model_info = get_closet_checkpoint_match(parsed_parameters.get("Model hash", None))
+ if model_info is not None:
+ p.override_settings['sd_model_checkpoint'] = model_info.name
+ elif sd_model_checkpoint_override:
+ p.override_settings['sd_model_checkpoint'] = sd_model_checkpoint_override
+ else:
+ p.override_settings.pop("sd_model_checkpoint", None)
+
+ if output_dir:
+ p.outpath_samples = output_dir
+ p.override_settings['save_to_dirs'] = False
+ p.override_settings['save_images_replace_action'] = "Add number suffix"
+ if p.n_iter > 1 or p.batch_size > 1:
+ p.override_settings['samples_filename_pattern'] = f'{image_path.stem}-[generation_number]'
+ else:
+ p.override_settings['samples_filename_pattern'] = f'{image_path.stem}'
+
proc = modules.scripts.scripts_img2img.run(p, *args)
+
if proc is None:
- if output_dir:
- p.outpath_samples = output_dir
- p.override_settings['save_to_dirs'] = False
- if p.n_iter > 1 or p.batch_size > 1:
- p.override_settings['samples_filename_pattern'] = f'{image_path.stem}-[generation_number]'
- else:
- p.override_settings['samples_filename_pattern'] = f'{image_path.stem}'
- process_images(p)
+ p.override_settings.pop('save_images_replace_action', None)
+ proc = process_images(p)
+ if not discard_further_results and proc:
+ if batch_results:
+ batch_results.images.extend(proc.images)
+ batch_results.infotexts.extend(proc.infotexts)
+ else:
+ batch_results = proc
-def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_name: str, mask_blur: int, mask_alpha: float, inpainting_fill: int, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *args):
+ if 0 <= shared.opts.img2img_batch_show_results_limit < len(batch_results.images):
+ discard_further_results = True
+ batch_results.images = batch_results.images[:int(shared.opts.img2img_batch_show_results_limit)]
+ batch_results.infotexts = batch_results.infotexts[:int(shared.opts.img2img_batch_show_results_limit)]
+
+ return batch_results
+
+
+def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_name: str, mask_blur: int, mask_alpha: float, inpainting_fill: int, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *args):
override_settings = create_override_settings_dict(override_settings_texts)
is_batch = mode == 5
if mode == 0: # img2img
- image = init_img.convert("RGB")
+ image = init_img
mask = None
elif mode == 1: # img2img sketch
- image = sketch.convert("RGB")
+ image = sketch
mask = None
elif mode == 2: # inpaint
image, mask = init_img_with_mask["image"], init_img_with_mask["mask"]
- mask = mask.split()[-1].convert("L").point(lambda x: 255 if x > 128 else 0)
- image = image.convert("RGB")
+ mask = processing.create_binary_mask(mask)
elif mode == 3: # inpaint sketch
image = inpaint_color_sketch
orig = inpaint_color_sketch_orig or inpaint_color_sketch
@@ -139,7 +168,6 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s mask = ImageEnhance.Brightness(mask).enhance(1 - mask_alpha / 100)
blur = ImageFilter.GaussianBlur(mask_blur)
image = Image.composite(image.filter(blur), orig, mask.filter(blur))
- image = image.convert("RGB")
elif mode == 4: # inpaint upload mask
image = init_img_inpaint
mask = init_mask_inpaint
@@ -166,12 +194,6 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s prompt=prompt,
negative_prompt=negative_prompt,
styles=prompt_styles,
- seed=seed,
- subseed=subseed,
- subseed_strength=subseed_strength,
- seed_resize_from_h=seed_resize_from_h,
- seed_resize_from_w=seed_resize_from_w,
- seed_enable_extras=seed_enable_extras,
sampler_name=sampler_name,
batch_size=batch_size,
n_iter=n_iter,
@@ -197,7 +219,7 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s p.user = request.username
- if shared.cmd_opts.enable_console_prompts:
+ if shared.opts.enable_console_prompts:
print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
if mask:
@@ -206,10 +228,10 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s with closing(p):
if is_batch:
assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
+ processed = process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
- process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
-
- processed = Processed(p, [], p.seed, "")
+ if processed is None:
+ processed = Processed(p, [], p.seed, "")
else:
processed = modules.scripts.scripts_img2img.run(p, *args)
if processed is None:
diff --git a/modules/initialize.py b/modules/initialize.py index f24f7637..ac95fc6f 100644 --- a/modules/initialize.py +++ b/modules/initialize.py @@ -151,8 +151,8 @@ def initialize_rest(*, reload_script_modules=False): from modules import devices
devices.first_time_calculation()
-
- Thread(target=load_model).start()
+ if not shared.cmd_opts.skip_load_model_at_start:
+ Thread(target=load_model).start()
from modules import shared_items
shared_items.reload_hypernetworks()
diff --git a/modules/initialize_util.py b/modules/initialize_util.py index d8370576..2e9b6d89 100644 --- a/modules/initialize_util.py +++ b/modules/initialize_util.py @@ -132,10 +132,33 @@ def get_gradio_auth_creds(): yield cred
+def dumpstacks():
+ import threading
+ import traceback
+
+ id2name = {th.ident: th.name for th in threading.enumerate()}
+ code = []
+ for threadId, stack in sys._current_frames().items():
+ code.append(f"\n# Thread: {id2name.get(threadId, '')}({threadId})")
+ for filename, lineno, name, line in traceback.extract_stack(stack):
+ code.append(f"""File: "{filename}", line {lineno}, in {name}""")
+ if line:
+ code.append(" " + line.strip())
+
+ print("\n".join(code))
+
+
def configure_sigint_handler():
# make the program just exit at ctrl+c without waiting for anything
+
+ from modules import shared
+
def sigint_handler(sig, frame):
print(f'Interrupted with signal {sig} in {frame}')
+
+ if shared.opts.dump_stacks_on_signal:
+ dumpstacks()
+
os._exit(0)
if not os.environ.get("COVERAGE_RUN"):
diff --git a/modules/interrogate.py b/modules/interrogate.py index a3ae1dd5..3045560d 100644 --- a/modules/interrogate.py +++ b/modules/interrogate.py @@ -186,9 +186,8 @@ class InterrogateModels: res = ""
shared.state.begin(job="interrogate")
try:
- if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
- lowvram.send_everything_to_cpu()
- devices.torch_gc()
+ lowvram.send_everything_to_cpu()
+ devices.torch_gc()
self.load()
diff --git a/modules/launch_utils.py b/modules/launch_utils.py index 90c00dd2..264ec9ca 100644 --- a/modules/launch_utils.py +++ b/modules/launch_utils.py @@ -3,6 +3,7 @@ import logging import re
import subprocess
import os
+import shutil
import sys
import importlib.util
import platform
@@ -63,7 +64,7 @@ Use --skip-python-version-check to suppress this warning. @lru_cache()
def commit_hash():
try:
- return subprocess.check_output([git, "rev-parse", "HEAD"], shell=False, encoding='utf8').strip()
+ return subprocess.check_output([git, "-C", script_path, "rev-parse", "HEAD"], shell=False, encoding='utf8').strip()
except Exception:
return "<none>"
@@ -71,7 +72,7 @@ def commit_hash(): @lru_cache()
def git_tag():
try:
- return subprocess.check_output([git, "describe", "--tags"], shell=False, encoding='utf8').strip()
+ return subprocess.check_output([git, "-C", script_path, "describe", "--tags"], shell=False, encoding='utf8').strip()
except Exception:
try:
@@ -152,10 +153,8 @@ def run_git(dir, name, command, desc=None, errdesc=None, custom_env=None, live: try:
return run(f'"{git}" -C "{dir}" {command}', desc=desc, errdesc=errdesc, custom_env=custom_env, live=live)
except RuntimeError:
- pass
-
- if not autofix:
- return None
+ if not autofix:
+ raise
print(f"{errdesc}, attempting autofix...")
git_fix_workspace(dir, name)
@@ -174,13 +173,20 @@ def git_clone(url, dir, name, commithash=None): if current_hash == commithash:
return
- run_git('fetch', f"Fetching updates for {name}...", f"Couldn't fetch {name}")
+ if run_git(dir, name, 'config --get remote.origin.url', None, f"Couldn't determine {name}'s origin URL", live=False).strip() != url:
+ run_git(dir, name, f'remote set-url origin "{url}"', None, f"Failed to set {name}'s origin URL", live=False)
- run_git('checkout', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}", live=True)
+ run_git(dir, name, 'fetch', f"Fetching updates for {name}...", f"Couldn't fetch {name}", autofix=False)
+
+ run_git(dir, name, f'checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}", live=True)
return
- run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
+ try:
+ run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
+ except RuntimeError:
+ shutil.rmtree(dir, ignore_errors=True)
+ raise
if commithash is not None:
run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
@@ -222,7 +228,9 @@ def run_extension_installer(extension_dir): env = os.environ.copy()
env['PYTHONPATH'] = f"{os.path.abspath('.')}{os.pathsep}{env.get('PYTHONPATH', '')}"
- print(run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env))
+ stdout = run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env).strip()
+ if stdout:
+ print(stdout)
except Exception as e:
errors.report(str(e))
@@ -240,7 +248,7 @@ def list_extensions(settings_file): disabled_extensions = set(settings.get('disabled_extensions', []))
disable_all_extensions = settings.get('disable_all_extensions', 'none')
- if disable_all_extensions != 'none':
+ if disable_all_extensions != 'none' or args.disable_extra_extensions or args.disable_all_extensions or not os.path.isdir(extensions_dir):
return []
return [x for x in os.listdir(extensions_dir) if x not in disabled_extensions]
@@ -305,7 +313,6 @@ def prepare_environment(): requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.20')
- gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "https://github.com/TencentARC/GFPGAN/archive/8d2447a2d918f8eba5a4a01463fd48e45126a379.zip")
clip_package = os.environ.get('CLIP_PACKAGE', "https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip")
openclip_package = os.environ.get('OPENCLIP_PACKAGE', "https://github.com/mlfoundations/open_clip/archive/bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip")
@@ -316,13 +323,13 @@ def prepare_environment(): blip_repo = os.environ.get('BLIP_REPO', 'https://github.com/salesforce/BLIP.git')
stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf")
- stable_diffusion_xl_commit_hash = os.environ.get('STABLE_DIFFUSION_XL_COMMIT_HASH', "5c10deee76adad0032b412294130090932317a87")
- k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "c9fe758757e022f05ca5a53fa8fac28889e4f1cf")
+ stable_diffusion_xl_commit_hash = os.environ.get('STABLE_DIFFUSION_XL_COMMIT_HASH', "45c443b316737a4ab6e40413d7794a7f5657c19f")
+ k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "ab527a9a6d347f364e3d185ba6d714e22d80cb3c")
codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
try:
- # the existance of this file is a signal to webui.sh/bat that webui needs to be restarted when it stops execution
+ # the existence of this file is a signal to webui.sh/bat that webui needs to be restarted when it stops execution
os.remove(os.path.join(script_path, "tmp", "restart"))
os.environ.setdefault('SD_WEBUI_RESTARTING', '1')
except OSError:
@@ -352,11 +359,6 @@ def prepare_environment(): )
startup_timer.record("torch GPU test")
-
- if not is_installed("gfpgan"):
- run_pip(f"install {gfpgan_package}", "gfpgan")
- startup_timer.record("install gfpgan")
-
if not is_installed("clip"):
run_pip(f"install {clip_package}", "clip")
startup_timer.record("install clip")
@@ -366,17 +368,7 @@ def prepare_environment(): startup_timer.record("install open_clip")
if (not is_installed("xformers") or args.reinstall_xformers) and args.xformers:
- if platform.system() == "Windows":
- if platform.python_version().startswith("3.10"):
- run_pip(f"install -U -I --no-deps {xformers_package}", "xformers", live=True)
- else:
- print("Installation of xformers is not supported in this version of Python.")
- print("You can also check this and build manually: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers#building-xformers-on-windows-by-duckness")
- if not is_installed("xformers"):
- exit(0)
- elif platform.system() == "Linux":
- run_pip(f"install -U -I --no-deps {xformers_package}", "xformers")
-
+ run_pip(f"install -U -I --no-deps {xformers_package}", "xformers")
startup_timer.record("install xformers")
if not is_installed("ngrok") and args.ngrok:
@@ -404,7 +396,8 @@ def prepare_environment(): run_pip(f"install -r \"{requirements_file}\"", "requirements")
startup_timer.record("install requirements")
- run_extensions_installers(settings_file=args.ui_settings_file)
+ if not args.skip_install:
+ run_extensions_installers(settings_file=args.ui_settings_file)
if args.update_check:
version_check(commit)
@@ -441,3 +434,16 @@ def start(): webui.api_only()
else:
webui.webui()
+
+
+def dump_sysinfo():
+ from modules import sysinfo
+ import datetime
+
+ text = sysinfo.get()
+ filename = f"sysinfo-{datetime.datetime.utcnow().strftime('%Y-%m-%d-%H-%M')}.json"
+
+ with open(filename, "w", encoding="utf8") as file:
+ file.write(text)
+
+ return filename
diff --git a/modules/localization.py b/modules/localization.py index c1320288..108f792e 100644 --- a/modules/localization.py +++ b/modules/localization.py @@ -14,21 +14,24 @@ def list_localizations(dirname): if ext.lower() != ".json":
continue
- localizations[fn] = os.path.join(dirname, file)
+ localizations[fn] = [os.path.join(dirname, file)]
for file in scripts.list_scripts("localizations", ".json"):
fn, ext = os.path.splitext(file.filename)
- localizations[fn] = file.path
+ if fn not in localizations:
+ localizations[fn] = []
+ localizations[fn].append(file.path)
def localization_js(current_localization_name: str) -> str:
- fn = localizations.get(current_localization_name, None)
+ fns = localizations.get(current_localization_name, None)
data = {}
- if fn is not None:
- try:
- with open(fn, "r", encoding="utf8") as file:
- data = json.load(file)
- except Exception:
- errors.report(f"Error loading localization from {fn}", exc_info=True)
+ if fns is not None:
+ for fn in fns:
+ try:
+ with open(fn, "r", encoding="utf8") as file:
+ data.update(json.load(file))
+ except Exception:
+ errors.report(f"Error loading localization from {fn}", exc_info=True)
return f"window.localization = {json.dumps(data)}"
diff --git a/modules/logging_config.py b/modules/logging_config.py index 7db23d4b..79269875 100644 --- a/modules/logging_config.py +++ b/modules/logging_config.py @@ -1,16 +1,41 @@ import os
import logging
+try:
+ from tqdm.auto import tqdm
+
+ class TqdmLoggingHandler(logging.Handler):
+ def __init__(self, level=logging.INFO):
+ super().__init__(level)
+
+ def emit(self, record):
+ try:
+ msg = self.format(record)
+ tqdm.write(msg)
+ self.flush()
+ except Exception:
+ self.handleError(record)
+
+ TQDM_IMPORTED = True
+except ImportError:
+ # tqdm does not exist before first launch
+ # I will import once the UI finishes seting up the enviroment and reloads.
+ TQDM_IMPORTED = False
def setup_logging(loglevel):
if loglevel is None:
loglevel = os.environ.get("SD_WEBUI_LOG_LEVEL")
+ loghandlers = []
+
+ if TQDM_IMPORTED:
+ loghandlers.append(TqdmLoggingHandler())
+
if loglevel:
log_level = getattr(logging, loglevel.upper(), None) or logging.INFO
logging.basicConfig(
level=log_level,
format='%(asctime)s %(levelname)s [%(name)s] %(message)s',
datefmt='%Y-%m-%d %H:%M:%S',
+ handlers=loghandlers
)
-
diff --git a/modules/lowvram.py b/modules/lowvram.py index 96f52b7b..45701046 100644 --- a/modules/lowvram.py +++ b/modules/lowvram.py @@ -1,5 +1,5 @@ import torch
-from modules import devices
+from modules import devices, shared
module_in_gpu = None
cpu = torch.device("cpu")
@@ -14,6 +14,20 @@ def send_everything_to_cpu(): module_in_gpu = None
+def is_needed(sd_model):
+ return shared.cmd_opts.lowvram or shared.cmd_opts.medvram or shared.cmd_opts.medvram_sdxl and hasattr(sd_model, 'conditioner')
+
+
+def apply(sd_model):
+ enable = is_needed(sd_model)
+ shared.parallel_processing_allowed = not enable
+
+ if enable:
+ setup_for_low_vram(sd_model, not shared.cmd_opts.lowvram)
+ else:
+ sd_model.lowvram = False
+
+
def setup_for_low_vram(sd_model, use_medvram):
if getattr(sd_model, 'lowvram', False):
return
@@ -130,4 +144,4 @@ def setup_for_low_vram(sd_model, use_medvram): def is_enabled(sd_model):
- return getattr(sd_model, 'lowvram', False)
+ return sd_model.lowvram
diff --git a/modules/mac_specific.py b/modules/mac_specific.py index bce527cc..89256c5b 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -52,9 +52,6 @@ def cumsum_fix(input, cumsum_func, *args, **kwargs): if has_mps: - # MPS fix for randn in torchsde - CondFunc('torchsde._brownian.brownian_interval._randn', lambda _, size, dtype, device, seed: torch.randn(size, dtype=dtype, device=torch.device("cpu"), generator=torch.Generator(torch.device("cpu")).manual_seed(int(seed))).to(device), lambda _, size, dtype, device, seed: device.type == 'mps') - if platform.mac_ver()[0].startswith("13.2."): # MPS workaround for https://github.com/pytorch/pytorch/issues/95188, thanks to danieldk (https://github.com/explosion/curated-transformers/pull/124) CondFunc('torch.nn.functional.linear', lambda _, input, weight, bias: (torch.matmul(input, weight.t()) + bias) if bias is not None else torch.matmul(input, weight.t()), lambda _, input, weight, bias: input.numel() > 10485760) diff --git a/modules/options.py b/modules/options.py index db1fb157..ab40aff7 100644 --- a/modules/options.py +++ b/modules/options.py @@ -8,7 +8,7 @@ from modules.shared_cmd_options import cmd_opts class OptionInfo:
- def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None, comment_before='', comment_after='', infotext=None):
+ def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None, comment_before='', comment_after='', infotext=None, restrict_api=False):
self.default = default
self.label = label
self.component = component
@@ -26,6 +26,9 @@ class OptionInfo: self.infotext = infotext
+ self.restrict_api = restrict_api
+ """If True, the setting will not be accessible via API"""
+
def link(self, label, url):
self.comment_before += f"[<a href='{url}' target='_blank'>{label}</a>]"
return self
@@ -71,7 +74,7 @@ options_builtin_fields = {"data_labels", "data", "restricted_opts", "typemap"} class Options:
typemap = {int: float}
- def __init__(self, data_labels, restricted_opts):
+ def __init__(self, data_labels: dict[str, OptionInfo], restricted_opts):
self.data_labels = data_labels
self.data = {k: v.default for k, v in self.data_labels.items()}
self.restricted_opts = restricted_opts
@@ -113,14 +116,18 @@ class Options: return super(Options, self).__getattribute__(item)
- def set(self, key, value):
+ def set(self, key, value, is_api=False, run_callbacks=True):
"""sets an option and calls its onchange callback, returning True if the option changed and False otherwise"""
oldval = self.data.get(key, None)
if oldval == value:
return False
- if self.data_labels[key].do_not_save:
+ option = self.data_labels[key]
+ if option.do_not_save:
+ return False
+
+ if is_api and option.restrict_api:
return False
try:
@@ -128,9 +135,9 @@ class Options: except RuntimeError:
return False
- if self.data_labels[key].onchange is not None:
+ if run_callbacks and option.onchange is not None:
try:
- self.data_labels[key].onchange()
+ option.onchange()
except Exception as e:
errors.display(e, f"changing setting {key} to {value}")
setattr(self, key, oldval)
@@ -203,6 +210,8 @@ class Options: def add_option(self, key, info):
self.data_labels[key] = info
+ if key not in self.data:
+ self.data[key] = info.default
def reorder(self):
"""reorder settings so that all items related to section always go together"""
diff --git a/modules/patches.py b/modules/patches.py new file mode 100644 index 00000000..348235e7 --- /dev/null +++ b/modules/patches.py @@ -0,0 +1,64 @@ +from collections import defaultdict
+
+
+def patch(key, obj, field, replacement):
+ """Replaces a function in a module or a class.
+
+ Also stores the original function in this module, possible to be retrieved via original(key, obj, field).
+ If the function is already replaced by this caller (key), an exception is raised -- use undo() before that.
+
+ Arguments:
+ key: identifying information for who is doing the replacement. You can use __name__.
+ obj: the module or the class
+ field: name of the function as a string
+ replacement: the new function
+
+ Returns:
+ the original function
+ """
+
+ patch_key = (obj, field)
+ if patch_key in originals[key]:
+ raise RuntimeError(f"patch for {field} is already applied")
+
+ original_func = getattr(obj, field)
+ originals[key][patch_key] = original_func
+
+ setattr(obj, field, replacement)
+
+ return original_func
+
+
+def undo(key, obj, field):
+ """Undoes the peplacement by the patch().
+
+ If the function is not replaced, raises an exception.
+
+ Arguments:
+ key: identifying information for who is doing the replacement. You can use __name__.
+ obj: the module or the class
+ field: name of the function as a string
+
+ Returns:
+ Always None
+ """
+
+ patch_key = (obj, field)
+
+ if patch_key not in originals[key]:
+ raise RuntimeError(f"there is no patch for {field} to undo")
+
+ original_func = originals[key].pop(patch_key)
+ setattr(obj, field, original_func)
+
+ return None
+
+
+def original(key, obj, field):
+ """Returns the original function for the patch created by the patch() function"""
+ patch_key = (obj, field)
+
+ return originals[key].get(patch_key, None)
+
+
+originals = defaultdict(dict)
diff --git a/modules/paths.py b/modules/paths.py index 25052339..187b9496 100644 --- a/modules/paths.py +++ b/modules/paths.py @@ -1,6 +1,6 @@ import os
import sys
-from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir # noqa: F401
+from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, cwd # noqa: F401
import modules.safe # noqa: F401
diff --git a/modules/paths_internal.py b/modules/paths_internal.py index 005a9b0a..89131a54 100644 --- a/modules/paths_internal.py +++ b/modules/paths_internal.py @@ -8,6 +8,7 @@ import shlex commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
sys.argv += shlex.split(commandline_args)
+cwd = os.getcwd()
modules_path = os.path.dirname(os.path.realpath(__file__))
script_path = os.path.dirname(modules_path)
diff --git a/modules/postprocessing.py b/modules/postprocessing.py index 136e9c88..fd0c0cc9 100644 --- a/modules/postprocessing.py +++ b/modules/postprocessing.py @@ -11,37 +11,32 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, shared.state.begin(job="extras")
- image_data = []
- image_names = []
outputs = []
- if extras_mode == 1:
- for img in image_folder:
- if isinstance(img, Image.Image):
- image = img
- fn = ''
- else:
- image = Image.open(os.path.abspath(img.name))
- fn = os.path.splitext(img.orig_name)[0]
- image_data.append(image)
- image_names.append(fn)
- elif extras_mode == 2:
- assert not shared.cmd_opts.hide_ui_dir_config, '--hide-ui-dir-config option must be disabled'
- assert input_dir, 'input directory not selected'
-
- image_list = shared.listfiles(input_dir)
- for filename in image_list:
- try:
- image = Image.open(filename)
- except Exception:
- continue
- image_data.append(image)
- image_names.append(filename)
- else:
- assert image, 'image not selected'
-
- image_data.append(image)
- image_names.append(None)
+ def get_images(extras_mode, image, image_folder, input_dir):
+ if extras_mode == 1:
+ for img in image_folder:
+ if isinstance(img, Image.Image):
+ image = img
+ fn = ''
+ else:
+ image = Image.open(os.path.abspath(img.name))
+ fn = os.path.splitext(img.orig_name)[0]
+ yield image, fn
+ elif extras_mode == 2:
+ assert not shared.cmd_opts.hide_ui_dir_config, '--hide-ui-dir-config option must be disabled'
+ assert input_dir, 'input directory not selected'
+
+ image_list = shared.listfiles(input_dir)
+ for filename in image_list:
+ try:
+ image = Image.open(filename)
+ except Exception:
+ continue
+ yield image, filename
+ else:
+ assert image, 'image not selected'
+ yield image, None
if extras_mode == 2 and output_dir != '':
outpath = output_dir
@@ -50,14 +45,16 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, infotext = ''
- for image, name in zip(image_data, image_names):
+ for image_data, name in get_images(extras_mode, image, image_folder, input_dir):
+ image_data: Image.Image
+
shared.state.textinfo = name
- parameters, existing_pnginfo = images.read_info_from_image(image)
+ parameters, existing_pnginfo = images.read_info_from_image(image_data)
if parameters:
existing_pnginfo["parameters"] = parameters
- pp = scripts_postprocessing.PostprocessedImage(image.convert("RGB"))
+ pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB"))
scripts.scripts_postproc.run(pp, args)
@@ -78,8 +75,10 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, if extras_mode != 2 or show_extras_results:
outputs.append(pp.image)
- devices.torch_gc()
+ image_data.close()
+ devices.torch_gc()
+ shared.state.end()
return outputs, ui_common.plaintext_to_html(infotext), ''
diff --git a/modules/processing.py b/modules/processing.py index 44d47e8c..ac58ef86 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -1,9 +1,11 @@ +from __future__ import annotations
import json
import logging
import math
import os
import sys
import hashlib
+from dataclasses import dataclass, field
import torch
import numpy as np
@@ -11,7 +13,7 @@ from PIL import Image, ImageOps import random
import cv2
from skimage import exposure
-from typing import Any, Dict, List
+from typing import Any
import modules.sd_hijack
from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common, sd_unet, errors, rng
@@ -57,7 +59,7 @@ def apply_color_correction(correction, original_image): image = blendLayers(image, original_image, BlendType.LUMINOSITY)
- return image
+ return image.convert('RGB')
def apply_overlay(image, paste_loc, index, overlays):
@@ -79,12 +81,18 @@ def apply_overlay(image, paste_loc, index, overlays): return image
+def create_binary_mask(image):
+ if image.mode == 'RGBA' and image.getextrema()[-1] != (255, 255):
+ image = image.split()[-1].convert("L").point(lambda x: 255 if x > 128 else 0)
+ else:
+ image = image.convert('L')
+ return image
def txt2img_image_conditioning(sd_model, x, width, height):
if sd_model.model.conditioning_key in {'hybrid', 'concat'}: # Inpainting models
- # The "masked-image" in this case will just be all zeros since the entire image is masked.
- image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
+ # The "masked-image" in this case will just be all 0.5 since the entire image is masked.
+ image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5
image_conditioning = images_tensor_to_samples(image_conditioning, approximation_indexes.get(opts.sd_vae_encode_method))
# Add the fake full 1s mask to the first dimension.
@@ -104,97 +112,165 @@ def txt2img_image_conditioning(sd_model, x, width, height): return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
+@dataclass(repr=False)
class StableDiffusionProcessing:
- """
- The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
- """
+ sd_model: object = None
+ outpath_samples: str = None
+ outpath_grids: str = None
+ prompt: str = ""
+ prompt_for_display: str = None
+ negative_prompt: str = ""
+ styles: list[str] = None
+ seed: int = -1
+ subseed: int = -1
+ subseed_strength: float = 0
+ seed_resize_from_h: int = -1
+ seed_resize_from_w: int = -1
+ seed_enable_extras: bool = True
+ sampler_name: str = None
+ batch_size: int = 1
+ n_iter: int = 1
+ steps: int = 50
+ cfg_scale: float = 7.0
+ width: int = 512
+ height: int = 512
+ restore_faces: bool = None
+ tiling: bool = None
+ do_not_save_samples: bool = False
+ do_not_save_grid: bool = False
+ extra_generation_params: dict[str, Any] = None
+ overlay_images: list = None
+ eta: float = None
+ do_not_reload_embeddings: bool = False
+ denoising_strength: float = None
+ ddim_discretize: str = None
+ s_min_uncond: float = None
+ s_churn: float = None
+ s_tmax: float = None
+ s_tmin: float = None
+ s_noise: float = None
+ override_settings: dict[str, Any] = None
+ override_settings_restore_afterwards: bool = True
+ sampler_index: int = None
+ refiner_checkpoint: str = None
+ refiner_switch_at: float = None
+ token_merging_ratio = 0
+ token_merging_ratio_hr = 0
+ disable_extra_networks: bool = False
+
+ scripts_value: scripts.ScriptRunner = field(default=None, init=False)
+ script_args_value: list = field(default=None, init=False)
+ scripts_setup_complete: bool = field(default=False, init=False)
+
cached_uc = [None, None]
cached_c = [None, None]
- def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = None, tiling: bool = None, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_min_uncond: float = 0.0, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = None, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None):
- if sampler_index is not None:
+ comments: dict = None
+ sampler: sd_samplers_common.Sampler | None = field(default=None, init=False)
+ is_using_inpainting_conditioning: bool = field(default=False, init=False)
+ paste_to: tuple | None = field(default=None, init=False)
+
+ is_hr_pass: bool = field(default=False, init=False)
+
+ c: tuple = field(default=None, init=False)
+ uc: tuple = field(default=None, init=False)
+
+ rng: rng.ImageRNG | None = field(default=None, init=False)
+ step_multiplier: int = field(default=1, init=False)
+ color_corrections: list = field(default=None, init=False)
+
+ all_prompts: list = field(default=None, init=False)
+ all_negative_prompts: list = field(default=None, init=False)
+ all_seeds: list = field(default=None, init=False)
+ all_subseeds: list = field(default=None, init=False)
+ iteration: int = field(default=0, init=False)
+ main_prompt: str = field(default=None, init=False)
+ main_negative_prompt: str = field(default=None, init=False)
+
+ prompts: list = field(default=None, init=False)
+ negative_prompts: list = field(default=None, init=False)
+ seeds: list = field(default=None, init=False)
+ subseeds: list = field(default=None, init=False)
+ extra_network_data: dict = field(default=None, init=False)
+
+ user: str = field(default=None, init=False)
+
+ sd_model_name: str = field(default=None, init=False)
+ sd_model_hash: str = field(default=None, init=False)
+ sd_vae_name: str = field(default=None, init=False)
+ sd_vae_hash: str = field(default=None, init=False)
+
+ is_api: bool = field(default=False, init=False)
+
+ def __post_init__(self):
+ if self.sampler_index is not None:
print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
- self.outpath_samples: str = outpath_samples
- self.outpath_grids: str = outpath_grids
- self.prompt: str = prompt
- self.prompt_for_display: str = None
- self.negative_prompt: str = (negative_prompt or "")
- self.styles: list = styles or []
- self.seed: int = seed
- self.subseed: int = subseed
- self.subseed_strength: float = subseed_strength
- self.seed_resize_from_h: int = seed_resize_from_h
- self.seed_resize_from_w: int = seed_resize_from_w
- self.sampler_name: str = sampler_name
- self.batch_size: int = batch_size
- self.n_iter: int = n_iter
- self.steps: int = steps
- self.cfg_scale: float = cfg_scale
- self.width: int = width
- self.height: int = height
- self.restore_faces: bool = restore_faces
- self.tiling: bool = tiling
- self.do_not_save_samples: bool = do_not_save_samples
- self.do_not_save_grid: bool = do_not_save_grid
- self.extra_generation_params: dict = extra_generation_params or {}
- self.overlay_images = overlay_images
- self.eta = eta
- self.do_not_reload_embeddings = do_not_reload_embeddings
- self.paste_to = None
- self.color_corrections = None
- self.denoising_strength: float = denoising_strength
+ self.comments = {}
+
+ if self.styles is None:
+ self.styles = []
+
self.sampler_noise_scheduler_override = None
- self.ddim_discretize = ddim_discretize or opts.ddim_discretize
- self.s_min_uncond = s_min_uncond or opts.s_min_uncond
- self.s_churn = s_churn or opts.s_churn
- self.s_tmin = s_tmin or opts.s_tmin
- self.s_tmax = (s_tmax if s_tmax is not None else opts.s_tmax) or float('inf')
- self.s_noise = s_noise if s_noise is not None else opts.s_noise
- self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts}
- self.override_settings_restore_afterwards = override_settings_restore_afterwards
- self.is_using_inpainting_conditioning = False
- self.disable_extra_networks = False
- self.token_merging_ratio = 0
- self.token_merging_ratio_hr = 0
-
- if not seed_enable_extras:
+ self.s_min_uncond = self.s_min_uncond if self.s_min_uncond is not None else opts.s_min_uncond
+ self.s_churn = self.s_churn if self.s_churn is not None else opts.s_churn
+ self.s_tmin = self.s_tmin if self.s_tmin is not None else opts.s_tmin
+ self.s_tmax = (self.s_tmax if self.s_tmax is not None else opts.s_tmax) or float('inf')
+ self.s_noise = self.s_noise if self.s_noise is not None else opts.s_noise
+
+ self.extra_generation_params = self.extra_generation_params or {}
+ self.override_settings = self.override_settings or {}
+ self.script_args = self.script_args or {}
+
+ self.refiner_checkpoint_info = None
+
+ if not self.seed_enable_extras:
self.subseed = -1
self.subseed_strength = 0
self.seed_resize_from_h = 0
self.seed_resize_from_w = 0
- self.scripts = None
- self.script_args = script_args
- self.all_prompts = None
- self.all_negative_prompts = None
- self.all_seeds = None
- self.all_subseeds = None
- self.iteration = 0
- self.is_hr_pass = False
- self.sampler = None
- self.main_prompt = None
- self.main_negative_prompt = None
-
- self.prompts = None
- self.negative_prompts = None
- self.extra_network_data = None
- self.seeds = None
- self.subseeds = None
-
- self.step_multiplier = 1
self.cached_uc = StableDiffusionProcessing.cached_uc
self.cached_c = StableDiffusionProcessing.cached_c
- self.uc = None
- self.c = None
- self.rng: rng.ImageRNG = None
-
- self.user = None
@property
def sd_model(self):
return shared.sd_model
+ @sd_model.setter
+ def sd_model(self, value):
+ pass
+
+ @property
+ def scripts(self):
+ return self.scripts_value
+
+ @scripts.setter
+ def scripts(self, value):
+ self.scripts_value = value
+
+ if self.scripts_value and self.script_args_value and not self.scripts_setup_complete:
+ self.setup_scripts()
+
+ @property
+ def script_args(self):
+ return self.script_args_value
+
+ @script_args.setter
+ def script_args(self, value):
+ self.script_args_value = value
+
+ if self.scripts_value and self.script_args_value and not self.scripts_setup_complete:
+ self.setup_scripts()
+
+ def setup_scripts(self):
+ self.scripts_setup_complete = True
+
+ self.scripts.setup_scrips(self, is_ui=not self.is_api)
+
+ def comment(self, text):
+ self.comments[text] = 1
+
def txt2img_image_conditioning(self, x, width=None, height=None):
self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
@@ -220,7 +296,7 @@ class StableDiffusionProcessing: return conditioning
def edit_image_conditioning(self, source_image):
- conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
+ conditioning_image = shared.sd_model.encode_first_stage(source_image).mode()
return conditioning_image
@@ -310,15 +386,20 @@ class StableDiffusionProcessing: return self.token_merging_ratio or opts.token_merging_ratio
def setup_prompts(self):
- if type(self.prompt) == list:
+ if isinstance(self.prompt,list):
self.all_prompts = self.prompt
+ elif isinstance(self.negative_prompt, list):
+ self.all_prompts = [self.prompt] * len(self.negative_prompt)
else:
self.all_prompts = self.batch_size * self.n_iter * [self.prompt]
- if type(self.negative_prompt) == list:
+ if isinstance(self.negative_prompt, list):
self.all_negative_prompts = self.negative_prompt
else:
- self.all_negative_prompts = self.batch_size * self.n_iter * [self.negative_prompt]
+ self.all_negative_prompts = [self.negative_prompt] * len(self.all_prompts)
+
+ if len(self.all_prompts) != len(self.all_negative_prompts):
+ raise RuntimeError(f"Received a different number of prompts ({len(self.all_prompts)}) and negative prompts ({len(self.all_negative_prompts)})")
self.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, self.styles) for x in self.all_prompts]
self.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, self.styles) for x in self.all_negative_prompts]
@@ -326,12 +407,14 @@ class StableDiffusionProcessing: self.main_prompt = self.all_prompts[0]
self.main_negative_prompt = self.all_negative_prompts[0]
- def cached_params(self, required_prompts, steps, extra_network_data):
+ def cached_params(self, required_prompts, steps, extra_network_data, hires_steps=None, use_old_scheduling=False):
"""Returns parameters that invalidate the cond cache if changed"""
return (
required_prompts,
steps,
+ hires_steps,
+ use_old_scheduling,
opts.CLIP_stop_at_last_layers,
shared.sd_model.sd_checkpoint_info,
extra_network_data,
@@ -341,7 +424,7 @@ class StableDiffusionProcessing: self.height,
)
- def get_conds_with_caching(self, function, required_prompts, steps, caches, extra_network_data):
+ def get_conds_with_caching(self, function, required_prompts, steps, caches, extra_network_data, hires_steps=None):
"""
Returns the result of calling function(shared.sd_model, required_prompts, steps)
using a cache to store the result if the same arguments have been used before.
@@ -354,7 +437,13 @@ class StableDiffusionProcessing: caches is a list with items described above.
"""
- cached_params = self.cached_params(required_prompts, steps, extra_network_data)
+ if shared.opts.use_old_scheduling:
+ old_schedules = prompt_parser.get_learned_conditioning_prompt_schedules(required_prompts, steps, hires_steps, False)
+ new_schedules = prompt_parser.get_learned_conditioning_prompt_schedules(required_prompts, steps, hires_steps, True)
+ if old_schedules != new_schedules:
+ self.extra_generation_params["Old prompt editing timelines"] = True
+
+ cached_params = self.cached_params(required_prompts, steps, extra_network_data, hires_steps, shared.opts.use_old_scheduling)
for cache in caches:
if cache[0] is not None and cached_params == cache[0]:
@@ -363,7 +452,7 @@ class StableDiffusionProcessing: cache = caches[0]
with devices.autocast():
- cache[1] = function(shared.sd_model, required_prompts, steps)
+ cache[1] = function(shared.sd_model, required_prompts, steps, hires_steps, shared.opts.use_old_scheduling)
cache[0] = cached_params
return cache[1]
@@ -373,9 +462,15 @@ class StableDiffusionProcessing: negative_prompts = prompt_parser.SdConditioning(self.negative_prompts, width=self.width, height=self.height, is_negative_prompt=True)
sampler_config = sd_samplers.find_sampler_config(self.sampler_name)
- self.step_multiplier = 2 if sampler_config and sampler_config.options.get("second_order", False) else 1
- self.uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, self.steps * self.step_multiplier, [self.cached_uc], self.extra_network_data)
- self.c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, self.steps * self.step_multiplier, [self.cached_c], self.extra_network_data)
+ total_steps = sampler_config.total_steps(self.steps) if sampler_config else self.steps
+ self.step_multiplier = total_steps // self.steps
+ self.firstpass_steps = total_steps
+
+ self.uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, total_steps, [self.cached_uc], self.extra_network_data)
+ self.c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, total_steps, [self.cached_c], self.extra_network_data)
+
+ def get_conds(self):
+ return self.c, self.uc
def parse_extra_network_prompts(self):
self.prompts, self.extra_network_data = extra_networks.parse_prompts(self.prompts)
@@ -394,7 +489,7 @@ class Processed: self.subseed = subseed
self.subseed_strength = p.subseed_strength
self.info = info
- self.comments = comments
+ self.comments = "".join(f"{comment}\n" for comment in p.comments)
self.width = p.width
self.height = p.height
self.sampler_name = p.sampler_name
@@ -404,7 +499,10 @@ class Processed: self.batch_size = p.batch_size
self.restore_faces = p.restore_faces
self.face_restoration_model = opts.face_restoration_model if p.restore_faces else None
- self.sd_model_hash = shared.sd_model.sd_model_hash
+ self.sd_model_name = p.sd_model_name
+ self.sd_model_hash = p.sd_model_hash
+ self.sd_vae_name = p.sd_vae_name
+ self.sd_vae_hash = p.sd_vae_hash
self.seed_resize_from_w = p.seed_resize_from_w
self.seed_resize_from_h = p.seed_resize_from_h
self.denoising_strength = getattr(p, 'denoising_strength', None)
@@ -424,10 +522,10 @@ class Processed: self.s_noise = p.s_noise
self.s_min_uncond = p.s_min_uncond
self.sampler_noise_scheduler_override = p.sampler_noise_scheduler_override
- self.prompt = self.prompt if type(self.prompt) != list else self.prompt[0]
- self.negative_prompt = self.negative_prompt if type(self.negative_prompt) != list else self.negative_prompt[0]
- self.seed = int(self.seed if type(self.seed) != list else self.seed[0]) if self.seed is not None else -1
- self.subseed = int(self.subseed if type(self.subseed) != list else self.subseed[0]) if self.subseed is not None else -1
+ self.prompt = self.prompt if not isinstance(self.prompt, list) else self.prompt[0]
+ self.negative_prompt = self.negative_prompt if not isinstance(self.negative_prompt, list) else self.negative_prompt[0]
+ self.seed = int(self.seed if not isinstance(self.seed, list) else self.seed[0]) if self.seed is not None else -1
+ self.subseed = int(self.subseed if not isinstance(self.subseed, list) else self.subseed[0]) if self.subseed is not None else -1
self.is_using_inpainting_conditioning = p.is_using_inpainting_conditioning
self.all_prompts = all_prompts or p.all_prompts or [self.prompt]
@@ -435,6 +533,7 @@ class Processed: self.all_seeds = all_seeds or p.all_seeds or [self.seed]
self.all_subseeds = all_subseeds or p.all_subseeds or [self.subseed]
self.infotexts = infotexts or [info]
+ self.version = program_version()
def js(self):
obj = {
@@ -455,7 +554,10 @@ class Processed: "batch_size": self.batch_size,
"restore_faces": self.restore_faces,
"face_restoration_model": self.face_restoration_model,
+ "sd_model_name": self.sd_model_name,
"sd_model_hash": self.sd_model_hash,
+ "sd_vae_name": self.sd_vae_name,
+ "sd_vae_hash": self.sd_vae_hash,
"seed_resize_from_w": self.seed_resize_from_w,
"seed_resize_from_h": self.seed_resize_from_h,
"denoising_strength": self.denoising_strength,
@@ -466,6 +568,7 @@ class Processed: "job_timestamp": self.job_timestamp,
"clip_skip": self.clip_skip,
"is_using_inpainting_conditioning": self.is_using_inpainting_conditioning,
+ "version": self.version,
}
return json.dumps(obj)
@@ -574,10 +677,10 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Seed": p.all_seeds[0] if use_main_prompt else all_seeds[index],
"Face restoration": opts.face_restoration_model if p.restore_faces else None,
"Size": f"{p.width}x{p.height}",
- "Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
- "Model": (None if not opts.add_model_name_to_info else shared.sd_model.sd_checkpoint_info.name_for_extra),
- "VAE hash": sd_vae.get_loaded_vae_hash() if opts.add_model_hash_to_info else None,
- "VAE": sd_vae.get_loaded_vae_name() if opts.add_model_name_to_info else None,
+ "Model hash": p.sd_model_hash if opts.add_model_hash_to_info else None,
+ "Model": p.sd_model_name if opts.add_model_name_to_info else None,
+ "VAE hash": p.sd_vae_hash if opts.add_model_hash_to_info else None,
+ "VAE": p.sd_vae_name if opts.add_model_name_to_info else None,
"Variation seed": (None if p.subseed_strength == 0 else (p.all_subseeds[0] if use_main_prompt else all_subseeds[index])),
"Variation seed strength": (None if p.subseed_strength == 0 else p.subseed_strength),
"Seed resize from": (None if p.seed_resize_from_w <= 0 or p.seed_resize_from_h <= 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
@@ -588,7 +691,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Token merging ratio": None if token_merging_ratio == 0 else token_merging_ratio,
"Token merging ratio hr": None if not enable_hr or token_merging_ratio_hr == 0 else token_merging_ratio_hr,
"Init image hash": getattr(p, 'init_img_hash', None),
- "RNG": opts.randn_source if opts.randn_source != "GPU" and opts.randn_source != "NV" else None,
+ "RNG": opts.randn_source if opts.randn_source != "GPU" else None,
"NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond,
"Tiling": "True" if p.tiling else None,
**p.extra_generation_params,
@@ -608,16 +711,17 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if p.scripts is not None:
p.scripts.before_process(p)
- stored_opts = {k: opts.data[k] for k in p.override_settings.keys()}
+ stored_opts = {k: opts.data[k] if k in opts.data else opts.get_default(k) for k in p.override_settings.keys() if k in opts.data}
try:
# if no checkpoint override or the override checkpoint can't be found, remove override entry and load opts checkpoint
+ # and if after running refiner, the refiner model is not unloaded - webui swaps back to main model here, if model over is present it will be reloaded afterwards
if sd_models.checkpoint_aliases.get(p.override_settings.get('sd_model_checkpoint')) is None:
p.override_settings.pop('sd_model_checkpoint', None)
sd_models.reload_model_weights()
for k, v in p.override_settings.items():
- setattr(opts, k, v)
+ opts.set(k, v, is_api=True, run_callbacks=False)
if k == 'sd_model_checkpoint':
sd_models.reload_model_weights()
@@ -646,7 +750,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: def process_images_inner(p: StableDiffusionProcessing) -> Processed:
"""this is the main loop that both txt2img and img2img use; it calls func_init once inside all the scopes and func_sample once per batch"""
- if type(p.prompt) == list:
+ if isinstance(p.prompt, list):
assert(len(p.prompt) > 0)
else:
assert p.prompt is not None
@@ -662,19 +766,27 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.tiling is None:
p.tiling = opts.tiling
+ if p.refiner_checkpoint not in (None, "", "None", "none"):
+ p.refiner_checkpoint_info = sd_models.get_closet_checkpoint_match(p.refiner_checkpoint)
+ if p.refiner_checkpoint_info is None:
+ raise Exception(f'Could not find checkpoint with name {p.refiner_checkpoint}')
+
+ p.sd_model_name = shared.sd_model.sd_checkpoint_info.name_for_extra
+ p.sd_model_hash = shared.sd_model.sd_model_hash
+ p.sd_vae_name = sd_vae.get_loaded_vae_name()
+ p.sd_vae_hash = sd_vae.get_loaded_vae_hash()
+
modules.sd_hijack.model_hijack.apply_circular(p.tiling)
modules.sd_hijack.model_hijack.clear_comments()
- comments = {}
-
p.setup_prompts()
- if type(seed) == list:
+ if isinstance(seed, list):
p.all_seeds = seed
else:
p.all_seeds = [int(seed) + (x if p.subseed_strength == 0 else 0) for x in range(len(p.all_prompts))]
- if type(subseed) == list:
+ if isinstance(subseed, list):
p.all_subseeds = subseed
else:
p.all_subseeds = [int(subseed) + x for x in range(len(p.all_prompts))]
@@ -687,7 +799,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: infotexts = []
output_images = []
-
with torch.no_grad(), p.sd_model.ema_scope():
with devices.autocast():
p.init(p.all_prompts, p.all_seeds, p.all_subseeds)
@@ -710,6 +821,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if state.interrupted:
break
+ sd_models.reload_model_weights() # model can be changed for example by refiner
+
p.prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
p.negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size]
p.seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
@@ -744,7 +857,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: p.setup_conds()
for comment in model_hijack.comments:
- comments[comment] = 1
+ p.comment(comment)
p.extra_generation_params.update(model_hijack.extra_generation_params)
@@ -759,7 +872,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: else:
if opts.sd_vae_decode_method != 'Full':
p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method
-
x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
x_samples_ddim = torch.stack(x_samples_ddim).float()
@@ -772,6 +884,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: devices.torch_gc()
+ state.nextjob()
+
if p.scripts is not None:
p.scripts.postprocess_batch(p, x_samples_ddim, batch_number=n)
@@ -844,7 +958,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: devices.torch_gc()
- state.nextjob()
+ if not infotexts:
+ infotexts.append(Processed(p, []).infotext(p, 0))
p.color_corrections = None
@@ -873,7 +988,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: images_list=output_images,
seed=p.all_seeds[0],
info=infotexts[0],
- comments="".join(f"{comment}\n" for comment in comments),
subseed=p.all_subseeds[0],
index_of_first_image=index_of_first_image,
infotexts=infotexts,
@@ -897,49 +1011,51 @@ def old_hires_fix_first_pass_dimensions(width, height): return width, height
+@dataclass(repr=False)
class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
- sampler = None
+ enable_hr: bool = False
+ denoising_strength: float = 0.75
+ firstphase_width: int = 0
+ firstphase_height: int = 0
+ hr_scale: float = 2.0
+ hr_upscaler: str = None
+ hr_second_pass_steps: int = 0
+ hr_resize_x: int = 0
+ hr_resize_y: int = 0
+ hr_checkpoint_name: str = None
+ hr_sampler_name: str = None
+ hr_prompt: str = ''
+ hr_negative_prompt: str = ''
+
cached_hr_uc = [None, None]
cached_hr_c = [None, None]
- def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_checkpoint_name: str = None, hr_sampler_name: str = None, hr_prompt: str = '', hr_negative_prompt: str = '', **kwargs):
- super().__init__(**kwargs)
- self.enable_hr = enable_hr
- self.denoising_strength = denoising_strength
- self.hr_scale = hr_scale
- self.hr_upscaler = hr_upscaler
- self.hr_second_pass_steps = hr_second_pass_steps
- self.hr_resize_x = hr_resize_x
- self.hr_resize_y = hr_resize_y
- self.hr_upscale_to_x = hr_resize_x
- self.hr_upscale_to_y = hr_resize_y
- self.hr_checkpoint_name = hr_checkpoint_name
- self.hr_checkpoint_info = None
- self.hr_sampler_name = hr_sampler_name
- self.hr_prompt = hr_prompt
- self.hr_negative_prompt = hr_negative_prompt
- self.all_hr_prompts = None
- self.all_hr_negative_prompts = None
- self.latent_scale_mode = None
-
- if firstphase_width != 0 or firstphase_height != 0:
+ hr_checkpoint_info: dict = field(default=None, init=False)
+ hr_upscale_to_x: int = field(default=0, init=False)
+ hr_upscale_to_y: int = field(default=0, init=False)
+ truncate_x: int = field(default=0, init=False)
+ truncate_y: int = field(default=0, init=False)
+ applied_old_hires_behavior_to: tuple = field(default=None, init=False)
+ latent_scale_mode: dict = field(default=None, init=False)
+ hr_c: tuple | None = field(default=None, init=False)
+ hr_uc: tuple | None = field(default=None, init=False)
+ all_hr_prompts: list = field(default=None, init=False)
+ all_hr_negative_prompts: list = field(default=None, init=False)
+ hr_prompts: list = field(default=None, init=False)
+ hr_negative_prompts: list = field(default=None, init=False)
+ hr_extra_network_data: list = field(default=None, init=False)
+
+ def __post_init__(self):
+ super().__post_init__()
+
+ if self.firstphase_width != 0 or self.firstphase_height != 0:
self.hr_upscale_to_x = self.width
self.hr_upscale_to_y = self.height
- self.width = firstphase_width
- self.height = firstphase_height
-
- self.truncate_x = 0
- self.truncate_y = 0
- self.applied_old_hires_behavior_to = None
-
- self.hr_prompts = None
- self.hr_negative_prompts = None
- self.hr_extra_network_data = None
+ self.width = self.firstphase_width
+ self.height = self.firstphase_height
self.cached_hr_uc = StableDiffusionProcessingTxt2Img.cached_hr_uc
self.cached_hr_c = StableDiffusionProcessingTxt2Img.cached_hr_c
- self.hr_c = None
- self.hr_uc = None
def calculate_target_resolution(self):
if opts.use_old_hires_fix_width_height and self.applied_old_hires_behavior_to != (self.width, self.height):
@@ -1029,28 +1145,23 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if not self.enable_hr:
return samples
+ devices.torch_gc()
if self.latent_scale_mode is None:
decoded_samples = torch.stack(decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)).to(dtype=torch.float32)
else:
decoded_samples = None
- current = shared.sd_model.sd_checkpoint_info
- try:
- if self.hr_checkpoint_info is not None:
- self.sampler = None
- sd_models.reload_model_weights(info=self.hr_checkpoint_info)
- devices.torch_gc()
-
- return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
- finally:
- self.sampler = None
- sd_models.reload_model_weights(info=current)
- devices.torch_gc()
+ with sd_models.SkipWritingToConfig():
+ sd_models.reload_model_weights(info=self.hr_checkpoint_info)
+
+ return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
def sample_hr_pass(self, samples, decoded_samples, seeds, subseeds, subseed_strength, prompts):
- self.is_hr_pass = True
+ if shared.state.interrupted:
+ return samples
+ self.is_hr_pass = True
target_width = self.hr_upscale_to_x
target_height = self.hr_upscale_to_y
@@ -1133,10 +1244,12 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio())
+ self.sampler = None
+ devices.torch_gc()
+
decoded_samples = decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)
self.is_hr_pass = False
-
return decoded_samples
def close(self):
@@ -1159,12 +1272,12 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_negative_prompt == '':
self.hr_negative_prompt = self.negative_prompt
- if type(self.hr_prompt) == list:
+ if isinstance(self.hr_prompt, list):
self.all_hr_prompts = self.hr_prompt
else:
self.all_hr_prompts = self.batch_size * self.n_iter * [self.hr_prompt]
- if type(self.hr_negative_prompt) == list:
+ if isinstance(self.hr_negative_prompt, list):
self.all_hr_negative_prompts = self.hr_negative_prompt
else:
self.all_hr_negative_prompts = self.batch_size * self.n_iter * [self.hr_negative_prompt]
@@ -1179,10 +1292,20 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): hr_prompts = prompt_parser.SdConditioning(self.hr_prompts, width=self.hr_upscale_to_x, height=self.hr_upscale_to_y)
hr_negative_prompts = prompt_parser.SdConditioning(self.hr_negative_prompts, width=self.hr_upscale_to_x, height=self.hr_upscale_to_y, is_negative_prompt=True)
- self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, hr_negative_prompts, self.steps * self.step_multiplier, [self.cached_hr_uc, self.cached_uc], self.hr_extra_network_data)
- self.hr_c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, hr_prompts, self.steps * self.step_multiplier, [self.cached_hr_c, self.cached_c], self.hr_extra_network_data)
+ sampler_config = sd_samplers.find_sampler_config(self.hr_sampler_name or self.sampler_name)
+ steps = self.hr_second_pass_steps or self.steps
+ total_steps = sampler_config.total_steps(steps) if sampler_config else steps
+
+ self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, hr_negative_prompts, self.firstpass_steps, [self.cached_hr_uc, self.cached_uc], self.hr_extra_network_data, total_steps)
+ self.hr_c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, hr_prompts, self.firstpass_steps, [self.cached_hr_c, self.cached_c], self.hr_extra_network_data, total_steps)
def setup_conds(self):
+ if self.is_hr_pass:
+ # if we are in hr pass right now, the call is being made from the refiner, and we don't need to setup firstpass cons or switch model
+ self.hr_c = None
+ self.calculate_hr_conds()
+ return
+
super().setup_conds()
self.hr_uc = None
@@ -1192,7 +1315,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if shared.opts.hires_fix_use_firstpass_conds:
self.calculate_hr_conds()
- elif lowvram.is_enabled(shared.sd_model): # if in lowvram mode, we need to calculate conds right away, before the cond NN is unloaded
+ elif lowvram.is_enabled(shared.sd_model) and shared.sd_model.sd_checkpoint_info == sd_models.select_checkpoint(): # if in lowvram mode, we need to calculate conds right away, before the cond NN is unloaded
with devices.autocast():
extra_networks.activate(self, self.hr_extra_network_data)
@@ -1201,6 +1324,12 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): with devices.autocast():
extra_networks.activate(self, self.extra_network_data)
+ def get_conds(self):
+ if self.is_hr_pass:
+ return self.hr_c, self.hr_uc
+
+ return super().get_conds()
+
def parse_extra_network_prompts(self):
res = super().parse_extra_network_prompts()
@@ -1213,55 +1342,75 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): return res
+@dataclass(repr=False)
class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
- sampler = None
-
- def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, image_cfg_scale: float = None, mask: Any = None, mask_blur: int = None, mask_blur_x: int = 4, mask_blur_y: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, **kwargs):
- super().__init__(**kwargs)
-
- self.init_images = init_images
- self.resize_mode: int = resize_mode
- self.denoising_strength: float = denoising_strength
- self.image_cfg_scale: float = image_cfg_scale if shared.sd_model.cond_stage_key == "edit" else None
- self.init_latent = None
- self.image_mask = mask
- self.latent_mask = None
- self.mask_for_overlay = None
- if mask_blur is not None:
- mask_blur_x = mask_blur
- mask_blur_y = mask_blur
- self.mask_blur_x = mask_blur_x
- self.mask_blur_y = mask_blur_y
- self.inpainting_fill = inpainting_fill
- self.inpaint_full_res = inpaint_full_res
- self.inpaint_full_res_padding = inpaint_full_res_padding
- self.inpainting_mask_invert = inpainting_mask_invert
- self.initial_noise_multiplier = opts.initial_noise_multiplier if initial_noise_multiplier is None else initial_noise_multiplier
+ init_images: list = None
+ resize_mode: int = 0
+ denoising_strength: float = 0.75
+ image_cfg_scale: float = None
+ mask: Any = None
+ mask_blur_x: int = 4
+ mask_blur_y: int = 4
+ mask_blur: int = None
+ inpainting_fill: int = 0
+ inpaint_full_res: bool = True
+ inpaint_full_res_padding: int = 0
+ inpainting_mask_invert: int = 0
+ initial_noise_multiplier: float = None
+ latent_mask: Image = None
+
+ image_mask: Any = field(default=None, init=False)
+
+ nmask: torch.Tensor = field(default=None, init=False)
+ image_conditioning: torch.Tensor = field(default=None, init=False)
+ init_img_hash: str = field(default=None, init=False)
+ mask_for_overlay: Image = field(default=None, init=False)
+ init_latent: torch.Tensor = field(default=None, init=False)
+
+ def __post_init__(self):
+ super().__post_init__()
+
+ self.image_mask = self.mask
self.mask = None
- self.nmask = None
- self.image_conditioning = None
+ self.initial_noise_multiplier = opts.initial_noise_multiplier if self.initial_noise_multiplier is None else self.initial_noise_multiplier
+
+ @property
+ def mask_blur(self):
+ if self.mask_blur_x == self.mask_blur_y:
+ return self.mask_blur_x
+ return None
+
+ @mask_blur.setter
+ def mask_blur(self, value):
+ if isinstance(value, int):
+ self.mask_blur_x = value
+ self.mask_blur_y = value
def init(self, all_prompts, all_seeds, all_subseeds):
+ self.image_cfg_scale: float = self.image_cfg_scale if shared.sd_model.cond_stage_key == "edit" else None
+
self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
crop_region = None
image_mask = self.image_mask
if image_mask is not None:
- image_mask = image_mask.convert('L')
+ # image_mask is passed in as RGBA by Gradio to support alpha masks,
+ # but we still want to support binary masks.
+ image_mask = create_binary_mask(image_mask)
if self.inpainting_mask_invert:
image_mask = ImageOps.invert(image_mask)
if self.mask_blur_x > 0:
np_mask = np.array(image_mask)
- kernel_size = 2 * int(4 * self.mask_blur_x + 0.5) + 1
+ kernel_size = 2 * int(2.5 * self.mask_blur_x + 0.5) + 1
np_mask = cv2.GaussianBlur(np_mask, (kernel_size, 1), self.mask_blur_x)
image_mask = Image.fromarray(np_mask)
if self.mask_blur_y > 0:
np_mask = np.array(image_mask)
- kernel_size = 2 * int(4 * self.mask_blur_y + 0.5) + 1
+ kernel_size = 2 * int(2.5 * self.mask_blur_y + 0.5) + 1
np_mask = cv2.GaussianBlur(np_mask, (1, kernel_size), self.mask_blur_y)
image_mask = Image.fromarray(np_mask)
@@ -1367,7 +1516,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): elif self.inpainting_fill == 3:
self.init_latent = self.init_latent * self.mask
- self.image_conditioning = self.img2img_image_conditioning(image, self.init_latent, image_mask)
+ self.image_conditioning = self.img2img_image_conditioning(image * 2 - 1, self.init_latent, image_mask)
def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
x = self.rng.next()
diff --git a/modules/processing_scripts/refiner.py b/modules/processing_scripts/refiner.py new file mode 100644 index 00000000..29ccb78f --- /dev/null +++ b/modules/processing_scripts/refiner.py @@ -0,0 +1,49 @@ +import gradio as gr
+
+from modules import scripts, sd_models
+from modules.ui_common import create_refresh_button
+from modules.ui_components import InputAccordion
+
+
+class ScriptRefiner(scripts.ScriptBuiltinUI):
+ section = "accordions"
+ create_group = False
+
+ def __init__(self):
+ pass
+
+ def title(self):
+ return "Refiner"
+
+ def show(self, is_img2img):
+ return scripts.AlwaysVisible
+
+ def ui(self, is_img2img):
+ with InputAccordion(False, label="Refiner", elem_id=self.elem_id("enable")) as enable_refiner:
+ with gr.Row():
+ refiner_checkpoint = gr.Dropdown(label='Checkpoint', elem_id=self.elem_id("checkpoint"), choices=sd_models.checkpoint_tiles(), value='', tooltip="switch to another model in the middle of generation")
+ create_refresh_button(refiner_checkpoint, sd_models.list_models, lambda: {"choices": sd_models.checkpoint_tiles()}, self.elem_id("checkpoint_refresh"))
+
+ refiner_switch_at = gr.Slider(value=0.8, label="Switch at", minimum=0.01, maximum=1.0, step=0.01, elem_id=self.elem_id("switch_at"), tooltip="fraction of sampling steps when the switch to refiner model should happen; 1=never, 0.5=switch in the middle of generation")
+
+ def lookup_checkpoint(title):
+ info = sd_models.get_closet_checkpoint_match(title)
+ return None if info is None else info.title
+
+ self.infotext_fields = [
+ (enable_refiner, lambda d: 'Refiner' in d),
+ (refiner_checkpoint, lambda d: lookup_checkpoint(d.get('Refiner'))),
+ (refiner_switch_at, 'Refiner switch at'),
+ ]
+
+ return enable_refiner, refiner_checkpoint, refiner_switch_at
+
+ def setup(self, p, enable_refiner, refiner_checkpoint, refiner_switch_at):
+ # the actual implementation is in sd_samplers_common.py, apply_refiner
+
+ if not enable_refiner or refiner_checkpoint in (None, "", "None"):
+ p.refiner_checkpoint = None
+ p.refiner_switch_at = None
+ else:
+ p.refiner_checkpoint = refiner_checkpoint
+ p.refiner_switch_at = refiner_switch_at
diff --git a/modules/processing_scripts/seed.py b/modules/processing_scripts/seed.py new file mode 100644 index 00000000..dc9c2da5 --- /dev/null +++ b/modules/processing_scripts/seed.py @@ -0,0 +1,111 @@ +import json
+
+import gradio as gr
+
+from modules import scripts, ui, errors
+from modules.shared import cmd_opts
+from modules.ui_components import ToolButton
+
+
+class ScriptSeed(scripts.ScriptBuiltinUI):
+ section = "seed"
+ create_group = False
+
+ def __init__(self):
+ self.seed = None
+ self.reuse_seed = None
+ self.reuse_subseed = None
+
+ def title(self):
+ return "Seed"
+
+ def show(self, is_img2img):
+ return scripts.AlwaysVisible
+
+ def ui(self, is_img2img):
+ with gr.Row(elem_id=self.elem_id("seed_row")):
+ if cmd_opts.use_textbox_seed:
+ self.seed = gr.Textbox(label='Seed', value="", elem_id=self.elem_id("seed"), min_width=100)
+ else:
+ self.seed = gr.Number(label='Seed', value=-1, elem_id=self.elem_id("seed"), min_width=100, precision=0)
+
+ random_seed = ToolButton(ui.random_symbol, elem_id=self.elem_id("random_seed"), tooltip="Set seed to -1, which will cause a new random number to be used every time")
+ reuse_seed = ToolButton(ui.reuse_symbol, elem_id=self.elem_id("reuse_seed"), tooltip="Reuse seed from last generation, mostly useful if it was randomized")
+
+ seed_checkbox = gr.Checkbox(label='Extra', elem_id=self.elem_id("subseed_show"), value=False)
+
+ with gr.Group(visible=False, elem_id=self.elem_id("seed_extras")) as seed_extras:
+ with gr.Row(elem_id=self.elem_id("subseed_row")):
+ subseed = gr.Number(label='Variation seed', value=-1, elem_id=self.elem_id("subseed"), precision=0)
+ random_subseed = ToolButton(ui.random_symbol, elem_id=self.elem_id("random_subseed"))
+ reuse_subseed = ToolButton(ui.reuse_symbol, elem_id=self.elem_id("reuse_subseed"))
+ subseed_strength = gr.Slider(label='Variation strength', value=0.0, minimum=0, maximum=1, step=0.01, elem_id=self.elem_id("subseed_strength"))
+
+ with gr.Row(elem_id=self.elem_id("seed_resize_from_row")):
+ seed_resize_from_w = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from width", value=0, elem_id=self.elem_id("seed_resize_from_w"))
+ seed_resize_from_h = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from height", value=0, elem_id=self.elem_id("seed_resize_from_h"))
+
+ random_seed.click(fn=None, _js="function(){setRandomSeed('" + self.elem_id("seed") + "')}", show_progress=False, inputs=[], outputs=[])
+ random_subseed.click(fn=None, _js="function(){setRandomSeed('" + self.elem_id("subseed") + "')}", show_progress=False, inputs=[], outputs=[])
+
+ seed_checkbox.change(lambda x: gr.update(visible=x), show_progress=False, inputs=[seed_checkbox], outputs=[seed_extras])
+
+ self.infotext_fields = [
+ (self.seed, "Seed"),
+ (seed_checkbox, lambda d: "Variation seed" in d or "Seed resize from-1" in d),
+ (subseed, "Variation seed"),
+ (subseed_strength, "Variation seed strength"),
+ (seed_resize_from_w, "Seed resize from-1"),
+ (seed_resize_from_h, "Seed resize from-2"),
+ ]
+
+ self.on_after_component(lambda x: connect_reuse_seed(self.seed, reuse_seed, x.component, False), elem_id=f'generation_info_{self.tabname}')
+ self.on_after_component(lambda x: connect_reuse_seed(subseed, reuse_subseed, x.component, True), elem_id=f'generation_info_{self.tabname}')
+
+ return self.seed, seed_checkbox, subseed, subseed_strength, seed_resize_from_w, seed_resize_from_h
+
+ def setup(self, p, seed, seed_checkbox, subseed, subseed_strength, seed_resize_from_w, seed_resize_from_h):
+ p.seed = seed
+
+ if seed_checkbox and subseed_strength > 0:
+ p.subseed = subseed
+ p.subseed_strength = subseed_strength
+
+ if seed_checkbox and seed_resize_from_w > 0 and seed_resize_from_h > 0:
+ p.seed_resize_from_w = seed_resize_from_w
+ p.seed_resize_from_h = seed_resize_from_h
+
+
+
+def connect_reuse_seed(seed: gr.Number, reuse_seed: gr.Button, generation_info: gr.Textbox, is_subseed):
+ """ Connects a 'reuse (sub)seed' button's click event so that it copies last used
+ (sub)seed value from generation info the to the seed field. If copying subseed and subseed strength
+ was 0, i.e. no variation seed was used, it copies the normal seed value instead."""
+
+ def copy_seed(gen_info_string: str, index):
+ res = -1
+
+ try:
+ gen_info = json.loads(gen_info_string)
+ index -= gen_info.get('index_of_first_image', 0)
+
+ if is_subseed and gen_info.get('subseed_strength', 0) > 0:
+ all_subseeds = gen_info.get('all_subseeds', [-1])
+ res = all_subseeds[index if 0 <= index < len(all_subseeds) else 0]
+ else:
+ all_seeds = gen_info.get('all_seeds', [-1])
+ res = all_seeds[index if 0 <= index < len(all_seeds) else 0]
+
+ except json.decoder.JSONDecodeError:
+ if gen_info_string:
+ errors.report(f"Error parsing JSON generation info: {gen_info_string}")
+
+ return [res, gr.update()]
+
+ reuse_seed.click(
+ fn=copy_seed,
+ _js="(x, y) => [x, selected_gallery_index()]",
+ show_progress=False,
+ inputs=[generation_info, seed],
+ outputs=[seed, seed]
+ )
diff --git a/modules/progress.py b/modules/progress.py index f405f07f..69921de7 100644 --- a/modules/progress.py +++ b/modules/progress.py @@ -48,6 +48,7 @@ def add_task_to_queue(id_job): class ProgressRequest(BaseModel):
id_task: str = Field(default=None, title="Task ID", description="id of the task to get progress for")
id_live_preview: int = Field(default=-1, title="Live preview image ID", description="id of last received last preview image")
+ live_preview: bool = Field(default=True, title="Include live preview", description="boolean flag indicating whether to include the live preview image")
class ProgressResponse(BaseModel):
@@ -71,7 +72,12 @@ def progressapi(req: ProgressRequest): completed = req.id_task in finished_tasks
if not active:
- return ProgressResponse(active=active, queued=queued, completed=completed, id_live_preview=-1, textinfo="In queue..." if queued else "Waiting...")
+ textinfo = "Waiting..."
+ if queued:
+ sorted_queued = sorted(pending_tasks.keys(), key=lambda x: pending_tasks[x])
+ queue_index = sorted_queued.index(req.id_task)
+ textinfo = "In queue: {}/{}".format(queue_index + 1, len(sorted_queued))
+ return ProgressResponse(active=active, queued=queued, completed=completed, id_live_preview=-1, textinfo=textinfo)
progress = 0
@@ -89,31 +95,30 @@ def progressapi(req: ProgressRequest): predicted_duration = elapsed_since_start / progress if progress > 0 else None
eta = predicted_duration - elapsed_since_start if predicted_duration is not None else None
+ live_preview = None
id_live_preview = req.id_live_preview
- shared.state.set_current_image()
- if opts.live_previews_enable and shared.state.id_live_preview != req.id_live_preview:
- image = shared.state.current_image
- if image is not None:
- buffered = io.BytesIO()
-
- if opts.live_previews_image_format == "png":
- # using optimize for large images takes an enormous amount of time
- if max(*image.size) <= 256:
- save_kwargs = {"optimize": True}
+
+ if opts.live_previews_enable and req.live_preview:
+ shared.state.set_current_image()
+ if shared.state.id_live_preview != req.id_live_preview:
+ image = shared.state.current_image
+ if image is not None:
+ buffered = io.BytesIO()
+
+ if opts.live_previews_image_format == "png":
+ # using optimize for large images takes an enormous amount of time
+ if max(*image.size) <= 256:
+ save_kwargs = {"optimize": True}
+ else:
+ save_kwargs = {"optimize": False, "compress_level": 1}
+
else:
- save_kwargs = {"optimize": False, "compress_level": 1}
-
- else:
- save_kwargs = {}
-
- image.save(buffered, format=opts.live_previews_image_format, **save_kwargs)
- base64_image = base64.b64encode(buffered.getvalue()).decode('ascii')
- live_preview = f"data:image/{opts.live_previews_image_format};base64,{base64_image}"
- id_live_preview = shared.state.id_live_preview
- else:
- live_preview = None
- else:
- live_preview = None
+ save_kwargs = {}
+
+ image.save(buffered, format=opts.live_previews_image_format, **save_kwargs)
+ base64_image = base64.b64encode(buffered.getvalue()).decode('ascii')
+ live_preview = f"data:image/{opts.live_previews_image_format};base64,{base64_image}"
+ id_live_preview = shared.state.id_live_preview
return ProgressResponse(active=active, queued=queued, completed=completed, progress=progress, eta=eta, live_preview=live_preview, id_live_preview=id_live_preview, textinfo=shared.state.textinfo)
diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index 32d214e3..cba13455 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -2,10 +2,9 @@ from __future__ import annotations import re
from collections import namedtuple
-from typing import List
import lark
-# a prompt like this: "fantasy landscape with a [mountain:lake:0.25] and [an oak:a christmas tree:0.75][ in foreground::0.6][ in background:0.25] [shoddy:masterful:0.5]"
+# a prompt like this: "fantasy landscape with a [mountain:lake:0.25] and [an oak:a christmas tree:0.75][ in foreground::0.6][: in background:0.25] [shoddy:masterful:0.5]"
# will be represented with prompt_schedule like this (assuming steps=100):
# [25, 'fantasy landscape with a mountain and an oak in foreground shoddy']
# [50, 'fantasy landscape with a lake and an oak in foreground in background shoddy']
@@ -26,7 +25,7 @@ plain: /([^\\\[\]():|]|\\.)+/ %import common.SIGNED_NUMBER -> NUMBER
""")
-def get_learned_conditioning_prompt_schedules(prompts, steps):
+def get_learned_conditioning_prompt_schedules(prompts, base_steps, hires_steps=None, use_old_scheduling=False):
"""
>>> g = lambda p: get_learned_conditioning_prompt_schedules([p], 10)[0]
>>> g("test")
@@ -57,18 +56,39 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): [[1, 'female'], [2, 'male'], [3, 'female'], [4, 'male'], [5, 'female'], [6, 'male'], [7, 'female'], [8, 'male'], [9, 'female'], [10, 'male']]
>>> g("[fe|||]male")
[[1, 'female'], [2, 'male'], [3, 'male'], [4, 'male'], [5, 'female'], [6, 'male'], [7, 'male'], [8, 'male'], [9, 'female'], [10, 'male']]
+ >>> g = lambda p: get_learned_conditioning_prompt_schedules([p], 10, 10)[0]
+ >>> g("a [b:.5] c")
+ [[10, 'a b c']]
+ >>> g("a [b:1.5] c")
+ [[5, 'a c'], [10, 'a b c']]
"""
+ if hires_steps is None or use_old_scheduling:
+ int_offset = 0
+ flt_offset = 0
+ steps = base_steps
+ else:
+ int_offset = base_steps
+ flt_offset = 1.0
+ steps = hires_steps
+
def collect_steps(steps, tree):
res = [steps]
class CollectSteps(lark.Visitor):
def scheduled(self, tree):
- tree.children[-2] = float(tree.children[-2])
- if tree.children[-2] < 1:
- tree.children[-2] *= steps
- tree.children[-2] = min(steps, int(tree.children[-2]))
- res.append(tree.children[-2])
+ s = tree.children[-2]
+ v = float(s)
+ if use_old_scheduling:
+ v = v*steps if v<1 else v
+ else:
+ if "." in s:
+ v = (v - flt_offset) * steps
+ else:
+ v = (v - int_offset)
+ tree.children[-2] = min(steps, int(v))
+ if tree.children[-2] >= 1:
+ res.append(tree.children[-2])
def alternate(self, tree):
res.extend(range(1, steps+1))
@@ -86,7 +106,7 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): yield args[(step - 1) % len(args)]
def start(self, args):
def flatten(x):
- if type(x) == str:
+ if isinstance(x, str):
yield x
else:
for gen in x:
@@ -134,7 +154,7 @@ class SdConditioning(list): -def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps):
+def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps, hires_steps=None, use_old_scheduling=False):
"""converts a list of prompts into a list of prompt schedules - each schedule is a list of ScheduledPromptConditioning, specifying the comdition (cond),
and the sampling step at which this condition is to be replaced by the next one.
@@ -154,7 +174,7 @@ def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps): """
res = []
- prompt_schedules = get_learned_conditioning_prompt_schedules(prompts, steps)
+ prompt_schedules = get_learned_conditioning_prompt_schedules(prompts, steps, hires_steps, use_old_scheduling)
cache = {}
for prompt, prompt_schedule in zip(prompts, prompt_schedules):
@@ -219,17 +239,17 @@ def get_multicond_prompt_list(prompts: SdConditioning | list[str]): class ComposableScheduledPromptConditioning:
def __init__(self, schedules, weight=1.0):
- self.schedules: List[ScheduledPromptConditioning] = schedules
+ self.schedules: list[ScheduledPromptConditioning] = schedules
self.weight: float = weight
class MulticondLearnedConditioning:
def __init__(self, shape, batch):
self.shape: tuple = shape # the shape field is needed to send this object to DDIM/PLMS
- self.batch: List[List[ComposableScheduledPromptConditioning]] = batch
+ self.batch: list[list[ComposableScheduledPromptConditioning]] = batch
-def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearnedConditioning:
+def get_multicond_learned_conditioning(model, prompts, steps, hires_steps=None, use_old_scheduling=False) -> MulticondLearnedConditioning:
"""same as get_learned_conditioning, but returns a list of ScheduledPromptConditioning along with the weight objects for each prompt.
For each prompt, the list is obtained by splitting the prompt using the AND separator.
@@ -238,7 +258,7 @@ def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearne res_indexes, prompt_flat_list, prompt_indexes = get_multicond_prompt_list(prompts)
- learned_conditioning = get_learned_conditioning(model, prompt_flat_list, steps)
+ learned_conditioning = get_learned_conditioning(model, prompt_flat_list, steps, hires_steps, use_old_scheduling)
res = []
for indexes in res_indexes:
@@ -257,7 +277,7 @@ class DictWithShape(dict): return self["crossattn"].shape
-def reconstruct_cond_batch(c: List[List[ScheduledPromptConditioning]], current_step):
+def reconstruct_cond_batch(c: list[list[ScheduledPromptConditioning]], current_step):
param = c[0][0].cond
is_dict = isinstance(param, dict)
diff --git a/modules/realesrgan_model.py b/modules/realesrgan_model.py index 0700b853..02841c30 100644 --- a/modules/realesrgan_model.py +++ b/modules/realesrgan_model.py @@ -55,6 +55,7 @@ class UpscalerRealESRGAN(Upscaler): half=not cmd_opts.no_half and not cmd_opts.upcast_sampling,
tile=opts.ESRGAN_tile,
tile_pad=opts.ESRGAN_tile_overlap,
+ device=self.device,
)
upsampled = upsampler.enhance(np.array(img), outscale=info.scale)[0]
diff --git a/modules/restart.py b/modules/restart.py index 18eacaf3..2dd6493b 100644 --- a/modules/restart.py +++ b/modules/restart.py @@ -14,7 +14,9 @@ def is_restartable() -> bool: def restart_program() -> None: """creates file tmp/restart and immediately stops the process, which webui.bat/webui.sh interpret as a command to start webui again""" - (Path(script_path) / "tmp" / "restart").touch() + tmpdir = Path(script_path) / "tmp" + tmpdir.mkdir(parents=True, exist_ok=True) + (tmpdir / "restart").touch() stop_program() diff --git a/modules/rng.py b/modules/rng.py index f927a318..8934d39b 100644 --- a/modules/rng.py +++ b/modules/rng.py @@ -98,7 +98,7 @@ def slerp(val, low, high): class ImageRNG:
def __init__(self, shape, seeds, subseeds=None, subseed_strength=0.0, seed_resize_from_h=0, seed_resize_from_w=0):
- self.shape = shape
+ self.shape = tuple(map(int, shape))
self.seeds = seeds
self.subseeds = subseeds
self.subseed_strength = subseed_strength
@@ -110,7 +110,7 @@ class ImageRNG: self.is_first = True
def first(self):
- noise_shape = self.shape if self.seed_resize_from_h <= 0 or self.seed_resize_from_w <= 0 else (self.shape[0], self.seed_resize_from_h // 8, self.seed_resize_from_w // 8)
+ noise_shape = self.shape if self.seed_resize_from_h <= 0 or self.seed_resize_from_w <= 0 else (self.shape[0], int(self.seed_resize_from_h) // 8, int(self.seed_resize_from_w // 8))
xs = []
diff --git a/modules/script_callbacks.py b/modules/script_callbacks.py index 77ee55ee..9ed7ad21 100644 --- a/modules/script_callbacks.py +++ b/modules/script_callbacks.py @@ -1,7 +1,7 @@ import inspect
import os
from collections import namedtuple
-from typing import Optional, Dict, Any
+from typing import Optional, Any
from fastapi import FastAPI
from gradio import Blocks
@@ -28,6 +28,18 @@ class ImageSaveParams: """dictionary with parameters for image's PNG info data; infotext will have the key 'parameters'"""
+class ExtraNoiseParams:
+ def __init__(self, noise, x, xi):
+ self.noise = noise
+ """Random noise generated by the seed"""
+
+ self.x = x
+ """Latent representation of the image"""
+
+ self.xi = xi
+ """Noisy latent representation of the image"""
+
+
class CFGDenoiserParams:
def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps, text_cond, text_uncond):
self.x = x
@@ -100,6 +112,7 @@ callback_map = dict( callbacks_ui_settings=[],
callbacks_before_image_saved=[],
callbacks_image_saved=[],
+ callbacks_extra_noise=[],
callbacks_cfg_denoiser=[],
callbacks_cfg_denoised=[],
callbacks_cfg_after_cfg=[],
@@ -189,6 +202,14 @@ def image_saved_callback(params: ImageSaveParams): report_exception(c, 'image_saved_callback')
+def extra_noise_callback(params: ExtraNoiseParams):
+ for c in callback_map['callbacks_extra_noise']:
+ try:
+ c.callback(params)
+ except Exception:
+ report_exception(c, 'callbacks_extra_noise')
+
+
def cfg_denoiser_callback(params: CFGDenoiserParams):
for c in callback_map['callbacks_cfg_denoiser']:
try:
@@ -237,7 +258,7 @@ def image_grid_callback(params: ImageGridLoopParams): report_exception(c, 'image_grid')
-def infotext_pasted_callback(infotext: str, params: Dict[str, Any]):
+def infotext_pasted_callback(infotext: str, params: dict[str, Any]):
for c in callback_map['callbacks_infotext_pasted']:
try:
c.callback(infotext, params)
@@ -367,6 +388,14 @@ def on_image_saved(callback): add_callback(callback_map['callbacks_image_saved'], callback)
+def on_extra_noise(callback):
+ """register a function to be called before adding extra noise in img2img or hires fix;
+ The callback is called with one argument:
+ - params: ExtraNoiseParams - contains noise determined by seed and latent representation of image
+ """
+ add_callback(callback_map['callbacks_extra_noise'], callback)
+
+
def on_cfg_denoiser(callback):
"""register a function to be called in the kdiffussion cfg_denoiser method after building the inner model inputs.
The callback is called with one argument:
@@ -420,7 +449,7 @@ def on_infotext_pasted(callback): """register a function to be called before applying an infotext.
The callback is called with two arguments:
- infotext: str - raw infotext.
- - result: Dict[str, any] - parsed infotext parameters.
+ - result: dict[str, any] - parsed infotext parameters.
"""
add_callback(callback_map['callbacks_infotext_pasted'], callback)
diff --git a/modules/scripts.py b/modules/scripts.py index f7d060aa..b0689a23 100644 --- a/modules/scripts.py +++ b/modules/scripts.py @@ -3,6 +3,7 @@ import re import sys
import inspect
from collections import namedtuple
+from dataclasses import dataclass
import gradio as gr
@@ -21,6 +22,11 @@ class PostprocessBatchListArgs: self.images = images
+@dataclass
+class OnComponent:
+ component: gr.blocks.Block
+
+
class Script:
name = None
"""script's internal name derived from title"""
@@ -35,9 +41,13 @@ class Script: is_txt2img = False
is_img2img = False
+ tabname = None
group = None
- """A gr.Group component that has all script's UI inside it"""
+ """A gr.Group component that has all script's UI inside it."""
+
+ create_group = True
+ """If False, for alwayson scripts, a group component will not be created."""
infotext_fields = None
"""if set in ui(), this is a list of pairs of gradio component + text; the text will be used when
@@ -52,6 +62,15 @@ class Script: api_info = None
"""Generated value of type modules.api.models.ScriptInfo with information about the script for API"""
+ on_before_component_elem_id = None
+ """list of callbacks to be called before a component with an elem_id is created"""
+
+ on_after_component_elem_id = None
+ """list of callbacks to be called after a component with an elem_id is created"""
+
+ setup_for_ui_only = False
+ """If true, the script setup will only be run in Gradio UI, not in API"""
+
def title(self):
"""this function should return the title of the script. This is what will be displayed in the dropdown menu."""
@@ -90,9 +109,16 @@ class Script: pass
+ def setup(self, p, *args):
+ """For AlwaysVisible scripts, this function is called when the processing object is set up, before any processing starts.
+ args contains all values returned by components from ui().
+ """
+ pass
+
+
def before_process(self, p, *args):
"""
- This function is called very early before processing begins for AlwaysVisible scripts.
+ This function is called very early during processing begins for AlwaysVisible scripts.
You can modify the processing object (p) here, inject hooks, etc.
args contains all values returned by components from ui()
"""
@@ -212,6 +238,29 @@ class Script: pass
+ def on_before_component(self, callback, *, elem_id):
+ """
+ Calls callback before a component is created. The callback function is called with a single argument of type OnComponent.
+
+ May be called in show() or ui() - but it may be too late in latter as some components may already be created.
+
+ This function is an alternative to before_component in that it also cllows to run before a component is created, but
+ it doesn't require to be called for every created component - just for the one you need.
+ """
+ if self.on_before_component_elem_id is None:
+ self.on_before_component_elem_id = []
+
+ self.on_before_component_elem_id.append((elem_id, callback))
+
+ def on_after_component(self, callback, *, elem_id):
+ """
+ Calls callback after a component is created. The callback function is called with a single argument of type OnComponent.
+ """
+ if self.on_after_component_elem_id is None:
+ self.on_after_component_elem_id = []
+
+ self.on_after_component_elem_id.append((elem_id, callback))
+
def describe(self):
"""unused"""
return ""
@@ -220,7 +269,7 @@ class Script: """helper function to generate id for a HTML element, constructs final id out of script name, tab and user-supplied item_id"""
need_tabname = self.show(True) == self.show(False)
- tabkind = 'img2img' if self.is_img2img else 'txt2txt'
+ tabkind = 'img2img' if self.is_img2img else 'txt2img'
tabname = f"{tabkind}_" if need_tabname else ""
title = re.sub(r'[^a-z_0-9]', '', re.sub(r'\s', '_', self.title().lower()))
@@ -232,6 +281,19 @@ class Script: """
pass
+
+class ScriptBuiltinUI(Script):
+ setup_for_ui_only = True
+
+ def elem_id(self, item_id):
+ """helper function to generate id for a HTML element, constructs final id out of tab and user-supplied item_id"""
+
+ need_tabname = self.show(True) == self.show(False)
+ tabname = ('img2img' if self.is_img2img else 'txt2img') + "_" if need_tabname else ""
+
+ return f'{tabname}{item_id}'
+
+
current_basedir = paths.script_path
@@ -249,19 +311,113 @@ scripts_data = [] postprocessing_scripts_data = []
ScriptClassData = namedtuple("ScriptClassData", ["script_class", "path", "basedir", "module"])
+def topological_sort(dependencies):
+ """Accepts a dictionary mapping name to its dependencies, returns a list of names ordered according to dependencies.
+ Ignores errors relating to missing dependeencies or circular dependencies
+ """
+
+ visited = {}
+ result = []
+
+ def inner(name):
+ visited[name] = True
+
+ for dep in dependencies.get(name, []):
+ if dep in dependencies and dep not in visited:
+ inner(dep)
+
+ result.append(name)
+
+ for depname in dependencies:
+ if depname not in visited:
+ inner(depname)
+
+ return result
+
-def list_scripts(scriptdirname, extension):
- scripts_list = []
+@dataclass
+class ScriptWithDependencies:
+ script_canonical_name: str
+ file: ScriptFile
+ requires: list
+ load_before: list
+ load_after: list
- basedir = os.path.join(paths.script_path, scriptdirname)
- if os.path.exists(basedir):
- for filename in sorted(os.listdir(basedir)):
- scripts_list.append(ScriptFile(paths.script_path, filename, os.path.join(basedir, filename)))
- for ext in extensions.active():
- scripts_list += ext.list_files(scriptdirname, extension)
+def list_scripts(scriptdirname, extension, *, include_extensions=True):
+ scripts = {}
- scripts_list = [x for x in scripts_list if os.path.splitext(x.path)[1].lower() == extension and os.path.isfile(x.path)]
+ loaded_extensions = {ext.canonical_name: ext for ext in extensions.active()}
+ loaded_extensions_scripts = {ext.canonical_name: [] for ext in extensions.active()}
+
+ # build script dependency map
+ root_script_basedir = os.path.join(paths.script_path, scriptdirname)
+ if os.path.exists(root_script_basedir):
+ for filename in sorted(os.listdir(root_script_basedir)):
+ if not os.path.isfile(os.path.join(root_script_basedir, filename)):
+ continue
+
+ if os.path.splitext(filename)[1].lower() != extension:
+ continue
+
+ script_file = ScriptFile(paths.script_path, filename, os.path.join(root_script_basedir, filename))
+ scripts[filename] = ScriptWithDependencies(filename, script_file, [], [], [])
+
+ if include_extensions:
+ for ext in extensions.active():
+ extension_scripts_list = ext.list_files(scriptdirname, extension)
+ for extension_script in extension_scripts_list:
+ if not os.path.isfile(extension_script.path):
+ continue
+
+ script_canonical_name = ("builtin/" if ext.is_builtin else "") + ext.canonical_name + "/" + extension_script.filename
+ relative_path = scriptdirname + "/" + extension_script.filename
+
+ script = ScriptWithDependencies(
+ script_canonical_name=script_canonical_name,
+ file=extension_script,
+ requires=ext.metadata.get_script_requirements("Requires", relative_path, scriptdirname),
+ load_before=ext.metadata.get_script_requirements("Before", relative_path, scriptdirname),
+ load_after=ext.metadata.get_script_requirements("After", relative_path, scriptdirname),
+ )
+
+ scripts[script_canonical_name] = script
+ loaded_extensions_scripts[ext.canonical_name].append(script)
+
+ for script_canonical_name, script in scripts.items():
+ # load before requires inverse dependency
+ # in this case, append the script name into the load_after list of the specified script
+ for load_before in script.load_before:
+ # if this requires an individual script to be loaded before
+ other_script = scripts.get(load_before)
+ if other_script:
+ other_script.load_after.append(script_canonical_name)
+
+ # if this requires an extension
+ other_extension_scripts = loaded_extensions_scripts.get(load_before)
+ if other_extension_scripts:
+ for other_script in other_extension_scripts:
+ other_script.load_after.append(script_canonical_name)
+
+ # if After mentions an extension, remove it and instead add all of its scripts
+ for load_after in list(script.load_after):
+ if load_after not in scripts and load_after in loaded_extensions_scripts:
+ script.load_after.remove(load_after)
+
+ for other_script in loaded_extensions_scripts.get(load_after, []):
+ script.load_after.append(other_script.script_canonical_name)
+
+ dependencies = {}
+
+ for script_canonical_name, script in scripts.items():
+ for required_script in script.requires:
+ if required_script not in scripts and required_script not in loaded_extensions:
+ errors.report(f'Script "{script_canonical_name}" requires "{required_script}" to be loaded, but it is not.', exc_info=False)
+
+ dependencies[script_canonical_name] = script.load_after
+
+ ordered_scripts = topological_sort(dependencies)
+ scripts_list = [scripts[script_canonical_name].file for script_canonical_name in ordered_scripts]
return scripts_list
@@ -288,7 +444,7 @@ def load_scripts(): postprocessing_scripts_data.clear()
script_callbacks.clear_callbacks()
- scripts_list = list_scripts("scripts", ".py")
+ scripts_list = list_scripts("scripts", ".py") + list_scripts("modules/processing_scripts", ".py", include_extensions=False)
syspath = sys.path
@@ -302,15 +458,9 @@ def load_scripts(): elif issubclass(script_class, scripts_postprocessing.ScriptPostprocessing):
postprocessing_scripts_data.append(ScriptClassData(script_class, scriptfile.path, scriptfile.basedir, module))
- def orderby(basedir):
- # 1st webui, 2nd extensions-builtin, 3rd extensions
- priority = {os.path.join(paths.script_path, "extensions-builtin"):1, paths.script_path:0}
- for key in priority:
- if basedir.startswith(key):
- return priority[key]
- return 9999
-
- for scriptfile in sorted(scripts_list, key=lambda x: [orderby(x.basedir), x]):
+ # here the scripts_list is already ordered
+ # processing_script is not considered though
+ for scriptfile in scripts_list:
try:
if scriptfile.basedir != paths.script_path:
sys.path = [scriptfile.basedir] + sys.path
@@ -349,10 +499,17 @@ class ScriptRunner: self.selectable_scripts = []
self.alwayson_scripts = []
self.titles = []
+ self.title_map = {}
self.infotext_fields = []
self.paste_field_names = []
self.inputs = [None]
+ self.on_before_component_elem_id = {}
+ """dict of callbacks to be called before an element is created; key=elem_id, value=list of callbacks"""
+
+ self.on_after_component_elem_id = {}
+ """dict of callbacks to be called after an element is created; key=elem_id, value=list of callbacks"""
+
def initialize_scripts(self, is_img2img):
from modules import scripts_auto_postprocessing
@@ -367,6 +524,7 @@ class ScriptRunner: script.filename = script_data.path
script.is_txt2img = not is_img2img
script.is_img2img = is_img2img
+ script.tabname = "img2img" if is_img2img else "txt2img"
visibility = script.show(script.is_img2img)
@@ -379,6 +537,28 @@ class ScriptRunner: self.scripts.append(script)
self.selectable_scripts.append(script)
+ self.apply_on_before_component_callbacks()
+
+ def apply_on_before_component_callbacks(self):
+ for script in self.scripts:
+ on_before = script.on_before_component_elem_id or []
+ on_after = script.on_after_component_elem_id or []
+
+ for elem_id, callback in on_before:
+ if elem_id not in self.on_before_component_elem_id:
+ self.on_before_component_elem_id[elem_id] = []
+
+ self.on_before_component_elem_id[elem_id].append((callback, script))
+
+ for elem_id, callback in on_after:
+ if elem_id not in self.on_after_component_elem_id:
+ self.on_after_component_elem_id[elem_id] = []
+
+ self.on_after_component_elem_id[elem_id].append((callback, script))
+
+ on_before.clear()
+ on_after.clear()
+
def create_script_ui(self, script):
import modules.api.models as api_models
@@ -398,11 +578,15 @@ class ScriptRunner: arg_info = api_models.ScriptArg(label=control.label or "")
- for field in ("value", "minimum", "maximum", "step", "choices"):
+ for field in ("value", "minimum", "maximum", "step"):
v = getattr(control, field, None)
if v is not None:
setattr(arg_info, field, v)
+ choices = getattr(control, 'choices', None) # as of gradio 3.41, some items in choices are strings, and some are tuples where the first elem is the string
+ if choices is not None:
+ arg_info.choices = [x[0] if isinstance(x, tuple) else x for x in choices]
+
api_args.append(arg_info)
script.api_info = api_models.ScriptInfo(
@@ -429,15 +613,20 @@ class ScriptRunner: if script.alwayson and script.section != section:
continue
- with gr.Group(visible=script.alwayson) as group:
- self.create_script_ui(script)
+ if script.create_group:
+ with gr.Group(visible=script.alwayson) as group:
+ self.create_script_ui(script)
- script.group = group
+ script.group = group
+ else:
+ self.create_script_ui(script)
def prepare_ui(self):
self.inputs = [None]
def setup_ui(self):
+ all_titles = [wrap_call(script.title, script.filename, "title") or script.filename for script in self.scripts]
+ self.title_map = {title.lower(): script for title, script in zip(all_titles, self.scripts)}
self.titles = [wrap_call(script.title, script.filename, "title") or f"{script.filename} [error]" for script in self.selectable_scripts]
self.setup_ui_for_section(None)
@@ -484,6 +673,8 @@ class ScriptRunner: self.infotext_fields.append((dropdown, lambda x: gr.update(value=x.get('Script', 'None'))))
self.infotext_fields.extend([(script.group, onload_script_visibility) for script in self.selectable_scripts])
+ self.apply_on_before_component_callbacks()
+
return self.inputs
def run(self, p, *args):
@@ -577,6 +768,12 @@ class ScriptRunner: errors.report(f"Error running postprocess_image: {script.filename}", exc_info=True)
def before_component(self, component, **kwargs):
+ for callback, script in self.on_before_component_elem_id.get(kwargs.get("elem_id"), []):
+ try:
+ callback(OnComponent(component=component))
+ except Exception:
+ errors.report(f"Error running on_before_component: {script.filename}", exc_info=True)
+
for script in self.scripts:
try:
script.before_component(component, **kwargs)
@@ -584,12 +781,21 @@ class ScriptRunner: errors.report(f"Error running before_component: {script.filename}", exc_info=True)
def after_component(self, component, **kwargs):
+ for callback, script in self.on_after_component_elem_id.get(component.elem_id, []):
+ try:
+ callback(OnComponent(component=component))
+ except Exception:
+ errors.report(f"Error running on_after_component: {script.filename}", exc_info=True)
+
for script in self.scripts:
try:
script.after_component(component, **kwargs)
except Exception:
errors.report(f"Error running after_component: {script.filename}", exc_info=True)
+ def script(self, title):
+ return self.title_map.get(title.lower())
+
def reload_sources(self, cache):
for si, script in list(enumerate(self.scripts)):
args_from = script.args_from
@@ -608,7 +814,6 @@ class ScriptRunner: self.scripts[si].args_from = args_from
self.scripts[si].args_to = args_to
-
def before_hr(self, p):
for script in self.alwayson_scripts:
try:
@@ -617,6 +822,17 @@ class ScriptRunner: except Exception:
errors.report(f"Error running before_hr: {script.filename}", exc_info=True)
+ def setup_scrips(self, p, *, is_ui=True):
+ for script in self.alwayson_scripts:
+ if not is_ui and script.setup_for_ui_only:
+ continue
+
+ try:
+ script_args = p.script_args[script.args_from:script.args_to]
+ script.setup(p, *script_args)
+ except Exception:
+ errors.report(f"Error running setup: {script.filename}", exc_info=True)
+
scripts_txt2img: ScriptRunner = None
scripts_img2img: ScriptRunner = None
diff --git a/modules/sd_disable_initialization.py b/modules/sd_disable_initialization.py index 695c5736..8863107a 100644 --- a/modules/sd_disable_initialization.py +++ b/modules/sd_disable_initialization.py @@ -155,10 +155,16 @@ class LoadStateDictOnMeta(ReplaceHelper): ```
"""
- def __init__(self, state_dict, device):
+ def __init__(self, state_dict, device, weight_dtype_conversion=None):
super().__init__()
self.state_dict = state_dict
self.device = device
+ self.weight_dtype_conversion = weight_dtype_conversion or {}
+ self.default_dtype = self.weight_dtype_conversion.get('')
+
+ def get_weight_dtype(self, key):
+ key_first_term, _ = key.split('.', 1)
+ return self.weight_dtype_conversion.get(key_first_term, self.default_dtype)
def __enter__(self):
if shared.cmd_opts.disable_model_loading_ram_optimization:
@@ -167,23 +173,60 @@ class LoadStateDictOnMeta(ReplaceHelper): sd = self.state_dict
device = self.device
- def load_from_state_dict(original, self, state_dict, prefix, *args, **kwargs):
- params = [(name, param) for name, param in self._parameters.items() if param is not None and param.is_meta]
+ def load_from_state_dict(original, module, state_dict, prefix, *args, **kwargs):
+ used_param_keys = []
- for name, param in params:
- if param.is_meta:
- self._parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device), requires_grad=param.requires_grad)
+ for name, param in module._parameters.items():
+ if param is None:
+ continue
- original(self, state_dict, prefix, *args, **kwargs)
+ key = prefix + name
+ sd_param = sd.pop(key, None)
+ if sd_param is not None:
+ state_dict[key] = sd_param.to(dtype=self.get_weight_dtype(key))
+ used_param_keys.append(key)
- for name, _ in params:
+ if param.is_meta:
+ dtype = sd_param.dtype if sd_param is not None else param.dtype
+ module._parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device, dtype=dtype), requires_grad=param.requires_grad)
+
+ for name in module._buffers:
key = prefix + name
- if key in sd:
- del sd[key]
+ sd_param = sd.pop(key, None)
+ if sd_param is not None:
+ state_dict[key] = sd_param
+ used_param_keys.append(key)
+
+ original(module, state_dict, prefix, *args, **kwargs)
+
+ for key in used_param_keys:
+ state_dict.pop(key, None)
+
+ def load_state_dict(original, module, state_dict, strict=True):
+ """torch makes a lot of copies of the dictionary with weights, so just deleting entries from state_dict does not help
+ because the same values are stored in multiple copies of the dict. The trick used here is to give torch a dict with
+ all weights on meta device, i.e. deleted, and then it doesn't matter how many copies torch makes.
+
+ In _load_from_state_dict, the correct weight will be obtained from a single dict with the right weights (sd).
+
+ The dangerous thing about this is if _load_from_state_dict is not called, (if some exotic module overloads
+ the function and does not call the original) the state dict will just fail to load because weights
+ would be on the meta device.
+ """
+
+ if state_dict == sd:
+ state_dict = {k: v.to(device="meta", dtype=v.dtype) for k, v in state_dict.items()}
+
+ original(module, state_dict, strict=strict)
+
+ module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
+ module_load_from_state_dict = self.replace(torch.nn.Module, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(module_load_from_state_dict, *args, **kwargs))
linear_load_from_state_dict = self.replace(torch.nn.Linear, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(linear_load_from_state_dict, *args, **kwargs))
conv2d_load_from_state_dict = self.replace(torch.nn.Conv2d, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(conv2d_load_from_state_dict, *args, **kwargs))
mha_load_from_state_dict = self.replace(torch.nn.MultiheadAttention, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(mha_load_from_state_dict, *args, **kwargs))
+ layer_norm_load_from_state_dict = self.replace(torch.nn.LayerNorm, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(layer_norm_load_from_state_dict, *args, **kwargs))
+ group_norm_load_from_state_dict = self.replace(torch.nn.GroupNorm, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(group_norm_load_from_state_dict, *args, **kwargs))
def __exit__(self, exc_type, exc_val, exc_tb):
self.restore()
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 46652fbd..0157e19f 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -2,14 +2,15 @@ import torch from torch.nn.functional import silu
from types import MethodType
-from modules import devices, sd_hijack_optimizations, shared, script_callbacks, errors, sd_unet
+from modules import devices, sd_hijack_optimizations, shared, script_callbacks, errors, sd_unet, patches
from modules.hypernetworks import hypernetwork
from modules.shared import cmd_opts
-from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr
+from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr, xlmr_m18
import ldm.modules.attention
import ldm.modules.diffusionmodules.model
import ldm.modules.diffusionmodules.openaimodel
+import ldm.models.diffusion.ddpm
import ldm.models.diffusion.ddim
import ldm.models.diffusion.plms
import ldm.modules.encoders.modules
@@ -37,6 +38,8 @@ ldm.models.diffusion.ddpm.print = shared.ldm_print optimizers = []
current_optimizer: sd_hijack_optimizations.SdOptimization = None
+ldm_original_forward = patches.patch(__file__, ldm.modules.diffusionmodules.openaimodel.UNetModel, "forward", sd_unet.UNetModel_forward)
+sgm_original_forward = patches.patch(__file__, sgm.modules.diffusionmodules.openaimodel.UNetModel, "forward", sd_unet.UNetModel_forward)
def list_optimizers():
new_optimizers = script_callbacks.list_optimizers_callback()
@@ -181,6 +184,20 @@ class StableDiffusionModelHijack: errors.display(e, "applying cross attention optimization")
undo_optimizations()
+ def convert_sdxl_to_ssd(self, m):
+ """Converts an SDXL model to a Segmind Stable Diffusion model (see https://huggingface.co/segmind/SSD-1B)"""
+
+ delattr(m.model.diffusion_model.middle_block, '1')
+ delattr(m.model.diffusion_model.middle_block, '2')
+ for i in ['9', '8', '7', '6', '5', '4']:
+ delattr(m.model.diffusion_model.input_blocks[7][1].transformer_blocks, i)
+ delattr(m.model.diffusion_model.input_blocks[8][1].transformer_blocks, i)
+ delattr(m.model.diffusion_model.output_blocks[0][1].transformer_blocks, i)
+ delattr(m.model.diffusion_model.output_blocks[1][1].transformer_blocks, i)
+ delattr(m.model.diffusion_model.output_blocks[4][1].transformer_blocks, '1')
+ delattr(m.model.diffusion_model.output_blocks[5][1].transformer_blocks, '1')
+ devices.torch_gc()
+
def hijack(self, m):
conditioner = getattr(m, 'conditioner', None)
if conditioner:
@@ -208,7 +225,7 @@ class StableDiffusionModelHijack: else:
m.cond_stage_model = conditioner
- if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
+ if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation or type(m.cond_stage_model) == xlmr_m18.BertSeriesModelWithTransformation:
model_embeddings = m.cond_stage_model.roberta.embeddings
model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
m.cond_stage_model = sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords(m.cond_stage_model, self)
@@ -239,13 +256,34 @@ class StableDiffusionModelHijack: self.layers = flatten(m)
- if not hasattr(ldm.modules.diffusionmodules.openaimodel, 'copy_of_UNetModel_forward_for_webui'):
- ldm.modules.diffusionmodules.openaimodel.copy_of_UNetModel_forward_for_webui = ldm.modules.diffusionmodules.openaimodel.UNetModel.forward
+ import modules.models.diffusion.ddpm_edit
+
+ if isinstance(m, ldm.models.diffusion.ddpm.LatentDiffusion):
+ sd_unet.original_forward = ldm_original_forward
+ elif isinstance(m, modules.models.diffusion.ddpm_edit.LatentDiffusion):
+ sd_unet.original_forward = ldm_original_forward
+ elif isinstance(m, sgm.models.diffusion.DiffusionEngine):
+ sd_unet.original_forward = sgm_original_forward
+ else:
+ sd_unet.original_forward = None
- ldm.modules.diffusionmodules.openaimodel.UNetModel.forward = sd_unet.UNetModel_forward
def undo_hijack(self, m):
- if type(m.cond_stage_model) == sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords:
+ conditioner = getattr(m, 'conditioner', None)
+ if conditioner:
+ for i in range(len(conditioner.embedders)):
+ embedder = conditioner.embedders[i]
+ if isinstance(embedder, (sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords, sd_hijack_open_clip.FrozenOpenCLIPEmbedder2WithCustomWords)):
+ embedder.wrapped.model.token_embedding = embedder.wrapped.model.token_embedding.wrapped
+ conditioner.embedders[i] = embedder.wrapped
+ if isinstance(embedder, sd_hijack_clip.FrozenCLIPEmbedderForSDXLWithCustomWords):
+ embedder.wrapped.transformer.text_model.embeddings.token_embedding = embedder.wrapped.transformer.text_model.embeddings.token_embedding.wrapped
+ conditioner.embedders[i] = embedder.wrapped
+
+ if hasattr(m, 'cond_stage_model'):
+ delattr(m, 'cond_stage_model')
+
+ elif type(m.cond_stage_model) == sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords:
m.cond_stage_model = m.cond_stage_model.wrapped
elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
@@ -265,7 +303,8 @@ class StableDiffusionModelHijack: self.layers = None
self.clip = None
- ldm.modules.diffusionmodules.openaimodel.UNetModel.forward = ldm.modules.diffusionmodules.openaimodel.copy_of_UNetModel_forward_for_webui
+ sd_unet.original_forward = None
+
def apply_circular(self, enable):
if self.circular_enabled == enable:
diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 0e810eec..7f9e328d 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -1,6 +1,7 @@ from __future__ import annotations
import math
import psutil
+import platform
import torch
from torch import einsum
@@ -94,7 +95,10 @@ class SdOptimizationSdp(SdOptimizationSdpNoMem): class SdOptimizationSubQuad(SdOptimization):
name = "sub-quadratic"
cmd_opt = "opt_sub_quad_attention"
- priority = 10
+
+ @property
+ def priority(self):
+ return 1000 if shared.device.type == 'mps' else 10
def apply(self):
ldm.modules.attention.CrossAttention.forward = sub_quad_attention_forward
@@ -120,7 +124,7 @@ class SdOptimizationInvokeAI(SdOptimization): @property
def priority(self):
- return 1000 if not torch.cuda.is_available() else 10
+ return 1000 if shared.device.type != 'mps' and not torch.cuda.is_available() else 10
def apply(self):
ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward_invokeAI
@@ -427,7 +431,10 @@ def sub_quad_attention(q, k, v, q_chunk_size=1024, kv_chunk_size=None, kv_chunk_ qk_matmul_size_bytes = batch_x_heads * bytes_per_token * q_tokens * k_tokens
if chunk_threshold is None:
- chunk_threshold_bytes = int(get_available_vram() * 0.9) if q.device.type == 'mps' else int(get_available_vram() * 0.7)
+ if q.device.type == 'mps':
+ chunk_threshold_bytes = 268435456 * (2 if platform.processor() == 'i386' else bytes_per_token)
+ else:
+ chunk_threshold_bytes = int(get_available_vram() * 0.7)
elif chunk_threshold == 0:
chunk_threshold_bytes = None
else:
diff --git a/modules/sd_models.py b/modules/sd_models.py index 7a866a07..841402e8 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -1,22 +1,22 @@ import collections
import os.path
import sys
-import gc
import threading
import torch
import re
import safetensors.torch
-from omegaconf import OmegaConf
+from omegaconf import OmegaConf, ListConfig
from os import mkdir
from urllib import request
import ldm.modules.midas as midas
from ldm.util import instantiate_from_config
-from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config, sd_unet, sd_models_xl, cache, extra_networks, processing, lowvram, sd_hijack
+from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config, sd_unet, sd_models_xl, cache, extra_networks, processing, lowvram, sd_hijack, patches
from modules.timer import Timer
import tomesd
+import numpy as np
model_dir = "Stable-diffusion"
model_path = os.path.abspath(os.path.join(paths.models_path, model_dir))
@@ -27,15 +27,34 @@ checkpoint_alisases = checkpoint_aliases # for compatibility with old name checkpoints_loaded = collections.OrderedDict()
+def replace_key(d, key, new_key, value):
+ keys = list(d.keys())
+
+ d[new_key] = value
+
+ if key not in keys:
+ return d
+
+ index = keys.index(key)
+ keys[index] = new_key
+
+ new_d = {k: d[k] for k in keys}
+
+ d.clear()
+ d.update(new_d)
+ return d
+
+
class CheckpointInfo:
def __init__(self, filename):
self.filename = filename
abspath = os.path.abspath(filename)
+ abs_ckpt_dir = os.path.abspath(shared.cmd_opts.ckpt_dir) if shared.cmd_opts.ckpt_dir is not None else None
self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
- if shared.cmd_opts.ckpt_dir is not None and abspath.startswith(shared.cmd_opts.ckpt_dir):
- name = abspath.replace(shared.cmd_opts.ckpt_dir, '')
+ if abs_ckpt_dir and abspath.startswith(abs_ckpt_dir):
+ name = abspath.replace(abs_ckpt_dir, '')
elif abspath.startswith(model_path):
name = abspath.replace(model_path, '')
else:
@@ -91,9 +110,11 @@ class CheckpointInfo: if self.shorthash not in self.ids:
self.ids += [self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]', f'{self.name_for_extra} [{self.shorthash}]']
- checkpoints_list.pop(self.title, None)
+ old_title = self.title
self.title = f'{self.name} [{self.shorthash}]'
self.short_title = f'{self.name_for_extra} [{self.shorthash}]'
+
+ replace_key(checkpoints_list, old_title, self.title, self)
self.register()
return self.shorthash
@@ -109,9 +130,12 @@ except Exception: def setup_model():
+ """called once at startup to do various one-time tasks related to SD models"""
+
os.makedirs(model_path, exist_ok=True)
enable_midas_autodownload()
+ patch_given_betas()
def checkpoint_tiles(use_short=False):
@@ -147,6 +171,9 @@ re_strip_checksum = re.compile(r"\s*\[[^]]+]\s*$") def get_closet_checkpoint_match(search_string):
+ if not search_string:
+ return None
+
checkpoint_info = checkpoint_aliases.get(search_string, None)
if checkpoint_info is not None:
return checkpoint_info
@@ -286,6 +313,8 @@ def get_checkpoint_state_dict(checkpoint_info: CheckpointInfo, timer): if checkpoint_info in checkpoints_loaded:
# use checkpoint cache
print(f"Loading weights [{sd_model_hash}] from cache")
+ # move to end as latest
+ checkpoints_loaded.move_to_end(checkpoint_info)
return checkpoints_loaded[checkpoint_info]
print(f"Loading weights [{sd_model_hash}] from {checkpoint_info.filename}")
@@ -295,11 +324,27 @@ def get_checkpoint_state_dict(checkpoint_info: CheckpointInfo, timer): return res
+class SkipWritingToConfig:
+ """This context manager prevents load_model_weights from writing checkpoint name to the config when it loads weight."""
+
+ skip = False
+ previous = None
+
+ def __enter__(self):
+ self.previous = SkipWritingToConfig.skip
+ SkipWritingToConfig.skip = True
+ return self
+
+ def __exit__(self, exc_type, exc_value, exc_traceback):
+ SkipWritingToConfig.skip = self.previous
+
+
def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer):
sd_model_hash = checkpoint_info.calculate_shorthash()
timer.record("calculate hash")
- shared.opts.data["sd_model_checkpoint"] = checkpoint_info.title
+ if not SkipWritingToConfig.skip:
+ shared.opts.data["sd_model_checkpoint"] = checkpoint_info.title
if state_dict is None:
state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
@@ -307,16 +352,19 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer model.is_sdxl = hasattr(model, 'conditioner')
model.is_sd2 = not model.is_sdxl and hasattr(model.cond_stage_model, 'model')
model.is_sd1 = not model.is_sdxl and not model.is_sd2
-
+ model.is_ssd = model.is_sdxl and 'model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_q.weight' not in state_dict.keys()
if model.is_sdxl:
sd_models_xl.extend_sdxl(model)
- model.load_state_dict(state_dict, strict=False)
- timer.record("apply weights to model")
+ if model.is_ssd:
+ sd_hijack.model_hijack.convert_sdxl_to_ssd(model)
if shared.opts.sd_checkpoint_cache > 0:
# cache newly loaded model
- checkpoints_loaded[checkpoint_info] = state_dict
+ checkpoints_loaded[checkpoint_info] = state_dict.copy()
+
+ model.load_state_dict(state_dict, strict=False)
+ timer.record("apply weights to model")
del state_dict
@@ -324,7 +372,11 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer model.to(memory_format=torch.channels_last)
timer.record("apply channels_last")
- if not shared.cmd_opts.no_half:
+ if shared.cmd_opts.no_half:
+ model.float()
+ devices.dtype_unet = torch.float32
+ timer.record("apply float()")
+ else:
vae = model.first_stage_model
depth_model = getattr(model, 'depth_model', None)
@@ -340,9 +392,9 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer if depth_model:
model.depth_model = depth_model
+ devices.dtype_unet = torch.float16
timer.record("apply half()")
- devices.dtype_unet = torch.float16 if model.is_sdxl and not shared.cmd_opts.no_half else model.model.diffusion_model.dtype
devices.unet_needs_upcast = shared.cmd_opts.upcast_sampling and devices.dtype == torch.float16 and devices.dtype_unet == torch.float16
model.first_stage_model.to(devices.dtype_vae)
@@ -410,6 +462,20 @@ def enable_midas_autodownload(): midas.api.load_model = load_model_wrapper
+def patch_given_betas():
+ import ldm.models.diffusion.ddpm
+
+ def patched_register_schedule(*args, **kwargs):
+ """a modified version of register_schedule function that converts plain list from Omegaconf into numpy"""
+
+ if isinstance(args[1], ListConfig):
+ args = (args[0], np.array(args[1]), *args[2:])
+
+ original_register_schedule(*args, **kwargs)
+
+ original_register_schedule = patches.patch(__name__, ldm.models.diffusion.ddpm.DDPM, 'register_schedule', patched_register_schedule)
+
+
def repair_config(sd_config):
if not hasattr(sd_config.model.params, "use_ema"):
@@ -463,8 +529,12 @@ class SdModelData: return self.sd_model
- def set_sd_model(self, v):
+ def set_sd_model(self, v, already_loaded=False):
self.sd_model = v
+ if already_loaded:
+ sd_vae.base_vae = getattr(v, "base_vae", None)
+ sd_vae.loaded_vae_file = getattr(v, "loaded_vae_file", None)
+ sd_vae.checkpoint_info = v.sd_checkpoint_info
try:
self.loaded_sd_models.remove(v)
@@ -491,7 +561,7 @@ def get_empty_cond(sd_model): def send_model_to_cpu(m):
- if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
+ if m.lowvram:
lowvram.send_everything_to_cpu()
else:
m.to(devices.cpu)
@@ -499,10 +569,17 @@ def send_model_to_cpu(m): devices.torch_gc()
-def send_model_to_device(m):
- if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
- lowvram.setup_for_low_vram(m, shared.cmd_opts.medvram)
+def model_target_device(m):
+ if lowvram.is_needed(m):
+ return devices.cpu
else:
+ return devices.device
+
+
+def send_model_to_device(m):
+ lowvram.apply(m)
+
+ if not m.lowvram:
m.to(shared.device)
@@ -560,7 +637,15 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None): timer.record("create model")
- with sd_disable_initialization.LoadStateDictOnMeta(state_dict, devices.cpu):
+ if shared.cmd_opts.no_half:
+ weight_dtype_conversion = None
+ else:
+ weight_dtype_conversion = {
+ 'first_stage_model': None,
+ '': torch.float16,
+ }
+
+ with sd_disable_initialization.LoadStateDictOnMeta(state_dict, device=model_target_device(sd_model), weight_dtype_conversion=weight_dtype_conversion):
load_model_weights(sd_model, checkpoint_info, state_dict, timer)
timer.record("load weights from state dict")
@@ -623,10 +708,14 @@ def reuse_model_from_already_loaded(sd_model, checkpoint_info, timer): send_model_to_device(already_loaded)
timer.record("send model to device")
- model_data.set_sd_model(already_loaded)
- shared.opts.data["sd_model_checkpoint"] = already_loaded.sd_checkpoint_info.title
- shared.opts.data["sd_checkpoint_hash"] = already_loaded.sd_checkpoint_info.sha256
+ model_data.set_sd_model(already_loaded, already_loaded=True)
+
+ if not SkipWritingToConfig.skip:
+ shared.opts.data["sd_model_checkpoint"] = already_loaded.sd_checkpoint_info.title
+ shared.opts.data["sd_checkpoint_hash"] = already_loaded.sd_checkpoint_info.sha256
+
print(f"Using already loaded model {already_loaded.sd_checkpoint_info.title}: done in {timer.summary()}")
+ sd_vae.reload_vae_weights(already_loaded)
return model_data.sd_model
elif shared.opts.sd_checkpoints_limit > 1 and len(model_data.loaded_sd_models) < shared.opts.sd_checkpoints_limit:
print(f"Loading model {checkpoint_info.title} ({len(model_data.loaded_sd_models) + 1} out of {shared.opts.sd_checkpoints_limit})")
@@ -638,6 +727,10 @@ def reuse_model_from_already_loaded(sd_model, checkpoint_info, timer): sd_model = model_data.loaded_sd_models.pop()
model_data.sd_model = sd_model
+ sd_vae.base_vae = getattr(sd_model, "base_vae", None)
+ sd_vae.loaded_vae_file = getattr(sd_model, "loaded_vae_file", None)
+ sd_vae.checkpoint_info = sd_model.sd_checkpoint_info
+
print(f"Reusing loaded model {sd_model.sd_checkpoint_info.title} to load {checkpoint_info.title}")
return sd_model
else:
@@ -694,7 +787,7 @@ def reload_model_weights(sd_model=None, info=None): script_callbacks.model_loaded_callback(sd_model)
timer.record("script callbacks")
- if not shared.cmd_opts.lowvram and not shared.cmd_opts.medvram:
+ if not sd_model.lowvram:
sd_model.to(devices.device)
timer.record("move model to device")
@@ -707,17 +800,7 @@ def reload_model_weights(sd_model=None, info=None): def unload_model_weights(sd_model=None, info=None):
- timer = Timer()
-
- if model_data.sd_model:
- model_data.sd_model.to(devices.cpu)
- sd_hijack.model_hijack.undo_hijack(model_data.sd_model)
- model_data.sd_model = None
- sd_model = None
- gc.collect()
- devices.torch_gc()
-
- print(f"Unloaded weights {timer.summary()}.")
+ send_model_to_cpu(sd_model or shared.sd_model)
return sd_model
diff --git a/modules/sd_models_config.py b/modules/sd_models_config.py index 08dd03f1..deab2f6e 100644 --- a/modules/sd_models_config.py +++ b/modules/sd_models_config.py @@ -21,7 +21,7 @@ config_unopenclip = os.path.join(sd_repo_configs_path, "v2-1-stable-unclip-h-inf config_inpainting = os.path.join(sd_configs_path, "v1-inpainting-inference.yaml")
config_instruct_pix2pix = os.path.join(sd_configs_path, "instruct-pix2pix.yaml")
config_alt_diffusion = os.path.join(sd_configs_path, "alt-diffusion-inference.yaml")
-
+config_alt_diffusion_m18 = os.path.join(sd_configs_path, "alt-diffusion-m18-inference.yaml")
def is_using_v_parameterization_for_sd2(state_dict):
"""
@@ -95,7 +95,10 @@ def guess_model_config_from_state_dict(sd, filename): if diffusion_model_input.shape[1] == 8:
return config_instruct_pix2pix
+
if sd.get('cond_stage_model.roberta.embeddings.word_embeddings.weight', None) is not None:
+ if sd.get('cond_stage_model.transformation.weight').size()[0] == 1024:
+ return config_alt_diffusion_m18
return config_alt_diffusion
return config_default
diff --git a/modules/sd_models_types.py b/modules/sd_models_types.py new file mode 100644 index 00000000..f911fbb6 --- /dev/null +++ b/modules/sd_models_types.py @@ -0,0 +1,34 @@ +from ldm.models.diffusion.ddpm import LatentDiffusion
+from typing import TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+ from modules.sd_models import CheckpointInfo
+
+
+class WebuiSdModel(LatentDiffusion):
+ """This class is not actually instantinated, but its fields are created and fieeld by webui"""
+
+ lowvram: bool
+ """True if lowvram/medvram optimizations are enabled -- see modules.lowvram for more info"""
+
+ sd_model_hash: str
+ """short hash, 10 first characters of SHA1 hash of the model file; may be None if --no-hashing flag is used"""
+
+ sd_model_checkpoint: str
+ """path to the file on disk that model weights were obtained from"""
+
+ sd_checkpoint_info: 'CheckpointInfo'
+ """structure with additional information about the file with model's weights"""
+
+ is_sdxl: bool
+ """True if the model's architecture is SDXL or SSD"""
+
+ is_ssd: bool
+ """True if the model is SSD"""
+
+ is_sd2: bool
+ """True if the model's architecture is SD 2.x"""
+
+ is_sd1: bool
+ """True if the model's architecture is SD 1.x"""
diff --git a/modules/sd_samplers_cfg_denoiser.py b/modules/sd_samplers_cfg_denoiser.py index d826222c..b8101d38 100644 --- a/modules/sd_samplers_cfg_denoiser.py +++ b/modules/sd_samplers_cfg_denoiser.py @@ -38,16 +38,29 @@ class CFGDenoiser(torch.nn.Module): negative prompt.
"""
- def __init__(self, model, sampler):
+ def __init__(self, sampler):
super().__init__()
- self.inner_model = model
+ self.model_wrap = None
self.mask = None
self.nmask = None
self.init_latent = None
+ self.steps = None
+ """number of steps as specified by user in UI"""
+
+ self.total_steps = None
+ """expected number of calls to denoiser calculated from self.steps and specifics of the selected sampler"""
+
self.step = 0
self.image_cfg_scale = None
self.padded_cond_uncond = False
self.sampler = sampler
+ self.model_wrap = None
+ self.p = None
+ self.mask_before_denoising = False
+
+ @property
+ def inner_model(self):
+ raise NotImplementedError()
def combine_denoised(self, x_out, conds_list, uncond, cond_scale):
denoised_uncond = x_out[-uncond.shape[0]:]
@@ -68,10 +81,21 @@ class CFGDenoiser(torch.nn.Module): def get_pred_x0(self, x_in, x_out, sigma):
return x_out
+ def update_inner_model(self):
+ self.model_wrap = None
+
+ c, uc = self.p.get_conds()
+ self.sampler.sampler_extra_args['cond'] = c
+ self.sampler.sampler_extra_args['uncond'] = uc
+
def forward(self, x, sigma, uncond, cond, cond_scale, s_min_uncond, image_cond):
if state.interrupted or state.skipped:
raise sd_samplers_common.InterruptedException
+ if sd_samplers_common.apply_refiner(self):
+ cond = self.sampler.sampler_extra_args['cond']
+ uncond = self.sampler.sampler_extra_args['uncond']
+
# at self.image_cfg_scale == 1.0 produced results for edit model are the same as with normal sampling,
# so is_edit_model is set to False to support AND composition.
is_edit_model = shared.sd_model.cond_stage_key == "edit" and self.image_cfg_scale is not None and self.image_cfg_scale != 1.0
@@ -81,7 +105,7 @@ class CFGDenoiser(torch.nn.Module): assert not is_edit_model or all(len(conds) == 1 for conds in conds_list), "AND is not supported for InstructPix2Pix checkpoint (unless using Image CFG scale = 1.0)"
- if self.mask is not None:
+ if self.mask_before_denoising and self.mask is not None:
x = self.init_latent * self.mask + self.nmask * x
batch_size = len(conds_list)
@@ -141,7 +165,7 @@ class CFGDenoiser(torch.nn.Module): else:
cond_in = catenate_conds([tensor, uncond])
- if shared.batch_cond_uncond:
+ if shared.opts.batch_cond_uncond:
x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict(cond_in, image_cond_in))
else:
x_out = torch.zeros_like(x_in)
@@ -151,7 +175,7 @@ class CFGDenoiser(torch.nn.Module): x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(subscript_cond(cond_in, a, b), image_cond_in[a:b]))
else:
x_out = torch.zeros_like(x_in)
- batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
+ batch_size = batch_size*2 if shared.opts.batch_cond_uncond else batch_size
for batch_offset in range(0, tensor.shape[0], batch_size):
a = batch_offset
b = min(a + batch_size, tensor.shape[0])
@@ -183,6 +207,9 @@ class CFGDenoiser(torch.nn.Module): else:
denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
+ if not self.mask_before_denoising and self.mask is not None:
+ denoised = self.init_latent * self.mask + self.nmask * denoised
+
self.sampler.last_latent = self.get_pred_x0(torch.cat([x_in[i:i + 1] for i in denoised_image_indexes]), torch.cat([x_out[i:i + 1] for i in denoised_image_indexes]), sigma)
if opts.live_preview_content == "Prompt":
diff --git a/modules/sd_samplers_common.py b/modules/sd_samplers_common.py index 97bc0804..58efcad2 100644 --- a/modules/sd_samplers_common.py +++ b/modules/sd_samplers_common.py @@ -3,11 +3,20 @@ from collections import namedtuple import numpy as np
import torch
from PIL import Image
-from modules import devices, images, sd_vae_approx, sd_samplers, sd_vae_taesd, shared
+from modules import devices, images, sd_vae_approx, sd_samplers, sd_vae_taesd, shared, sd_models
from modules.shared import opts, state
import k_diffusion.sampling
-SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options'])
+
+SamplerDataTuple = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options'])
+
+
+class SamplerData(SamplerDataTuple):
+ def total_steps(self, steps):
+ if self.options.get("second_order", False):
+ steps = steps * 2
+
+ return steps
def setup_img2img_steps(p, steps=None):
@@ -26,22 +35,27 @@ approximation_indexes = {"Full": 0, "Approx NN": 1, "Approx cheap": 2, "TAESD": def samples_to_images_tensor(sample, approximation=None, model=None):
- '''latents -> images [-1, 1]'''
- if approximation is None:
+ """Transforms 4-channel latent space images into 3-channel RGB image tensors, with values in range [-1, 1]."""
+
+ if approximation is None or (shared.state.interrupted and opts.live_preview_fast_interrupt):
approximation = approximation_indexes.get(opts.show_progress_type, 0)
+ from modules import lowvram
+ if approximation == 0 and lowvram.is_enabled(shared.sd_model) and not shared.opts.live_preview_allow_lowvram_full:
+ approximation = 1
+
if approximation == 2:
x_sample = sd_vae_approx.cheap_approximation(sample)
elif approximation == 1:
x_sample = sd_vae_approx.model()(sample.to(devices.device, devices.dtype)).detach()
elif approximation == 3:
- x_sample = sample * 1.5
- x_sample = sd_vae_taesd.decoder_model()(x_sample.to(devices.device, devices.dtype)).detach()
+ x_sample = sd_vae_taesd.decoder_model()(sample.to(devices.device, devices.dtype)).detach()
x_sample = x_sample * 2 - 1
else:
if model is None:
model = shared.sd_model
- x_sample = model.decode_first_stage(sample.to(model.first_stage_model.dtype))
+ with devices.without_autocast(): # fixes an issue with unstable VAEs that are flaky even in fp32
+ x_sample = model.decode_first_stage(sample.to(model.first_stage_model.dtype))
return x_sample
@@ -81,9 +95,19 @@ def images_tensor_to_samples(image, approximation=None, model=None): else:
if model is None:
model = shared.sd_model
+ model.first_stage_model.to(devices.dtype_vae)
+
image = image.to(shared.device, dtype=devices.dtype_vae)
image = image * 2 - 1
- x_latent = model.get_first_stage_encoding(model.encode_first_stage(image))
+ if len(image) > 1:
+ x_latent = torch.stack([
+ model.get_first_stage_encoding(
+ model.encode_first_stage(torch.unsqueeze(img, 0))
+ )[0]
+ for img in image
+ ])
+ else:
+ x_latent = model.get_first_stage_encoding(model.encode_first_stage(image))
return x_latent
@@ -131,6 +155,42 @@ def replace_torchsde_browinan(): replace_torchsde_browinan()
+def apply_refiner(cfg_denoiser):
+ completed_ratio = cfg_denoiser.step / cfg_denoiser.total_steps
+ refiner_switch_at = cfg_denoiser.p.refiner_switch_at
+ refiner_checkpoint_info = cfg_denoiser.p.refiner_checkpoint_info
+
+ if refiner_switch_at is not None and completed_ratio < refiner_switch_at:
+ return False
+
+ if refiner_checkpoint_info is None or shared.sd_model.sd_checkpoint_info == refiner_checkpoint_info:
+ return False
+
+ if getattr(cfg_denoiser.p, "enable_hr", False):
+ is_second_pass = cfg_denoiser.p.is_hr_pass
+
+ if opts.hires_fix_refiner_pass == "first pass" and is_second_pass:
+ return False
+
+ if opts.hires_fix_refiner_pass == "second pass" and not is_second_pass:
+ return False
+
+ if opts.hires_fix_refiner_pass != "second pass":
+ cfg_denoiser.p.extra_generation_params['Hires refiner'] = opts.hires_fix_refiner_pass
+
+ cfg_denoiser.p.extra_generation_params['Refiner'] = refiner_checkpoint_info.short_title
+ cfg_denoiser.p.extra_generation_params['Refiner switch at'] = refiner_switch_at
+
+ with sd_models.SkipWritingToConfig():
+ sd_models.reload_model_weights(info=refiner_checkpoint_info)
+
+ devices.torch_gc()
+ cfg_denoiser.p.setup_conds()
+ cfg_denoiser.update_inner_model()
+
+ return True
+
+
class TorchHijack:
"""This is here to replace torch.randn_like of k-diffusion.
@@ -163,7 +223,7 @@ class Sampler: self.sampler_noises = None
self.stop_at = None
self.eta = None
- self.config = None # set by the function calling the constructor
+ self.config: SamplerData = None # set by the function calling the constructor
self.last_latent = None
self.s_min_uncond = None
self.s_churn = 0.0
@@ -173,11 +233,14 @@ class Sampler: self.eta_option_field = 'eta_ancestral'
self.eta_infotext_field = 'Eta'
+ self.eta_default = 1.0
self.conditioning_key = shared.sd_model.model.conditioning_key
- self.model_wrap = None
+ self.p = None
self.model_wrap_cfg = None
+ self.sampler_extra_args = None
+ self.options = {}
def callback_state(self, d):
step = d['i']
@@ -189,6 +252,8 @@ class Sampler: shared.total_tqdm.update()
def launch_sampling(self, steps, func):
+ self.model_wrap_cfg.steps = steps
+ self.model_wrap_cfg.total_steps = self.config.total_steps(steps)
state.sampling_steps = steps
state.sampling_step = 0
@@ -208,6 +273,8 @@ class Sampler: return p.steps
def initialize(self, p) -> dict:
+ self.p = p
+ self.model_wrap_cfg.p = p
self.model_wrap_cfg.mask = p.mask if hasattr(p, 'mask') else None
self.model_wrap_cfg.nmask = p.nmask if hasattr(p, 'nmask') else None
self.model_wrap_cfg.step = 0
@@ -223,7 +290,7 @@ class Sampler: extra_params_kwargs[param_name] = getattr(p, param_name)
if 'eta' in inspect.signature(self.func).parameters:
- if self.eta != 1.0:
+ if self.eta != self.eta_default:
p.extra_generation_params[self.eta_infotext_field] = self.eta
extra_params_kwargs['eta'] = self.eta
@@ -234,19 +301,19 @@ class Sampler: s_tmax = getattr(opts, 's_tmax', p.s_tmax) or self.s_tmax # 0 = inf
s_noise = getattr(opts, 's_noise', p.s_noise)
- if s_churn != self.s_churn:
+ if 's_churn' in extra_params_kwargs and s_churn != self.s_churn:
extra_params_kwargs['s_churn'] = s_churn
p.s_churn = s_churn
p.extra_generation_params['Sigma churn'] = s_churn
- if s_tmin != self.s_tmin:
+ if 's_tmin' in extra_params_kwargs and s_tmin != self.s_tmin:
extra_params_kwargs['s_tmin'] = s_tmin
p.s_tmin = s_tmin
p.extra_generation_params['Sigma tmin'] = s_tmin
- if s_tmax != self.s_tmax:
+ if 's_tmax' in extra_params_kwargs and s_tmax != self.s_tmax:
extra_params_kwargs['s_tmax'] = s_tmax
p.s_tmax = s_tmax
p.extra_generation_params['Sigma tmax'] = s_tmax
- if s_noise != self.s_noise:
+ if 's_noise' in extra_params_kwargs and s_noise != self.s_noise:
extra_params_kwargs['s_noise'] = s_noise
p.s_noise = s_noise
p.extra_generation_params['Sigma noise'] = s_noise
@@ -263,5 +330,8 @@ class Sampler: current_iter_seeds = p.all_seeds[p.iteration * p.batch_size:(p.iteration + 1) * p.batch_size]
return BrownianTreeNoiseSampler(x, sigma_min, sigma_max, seed=current_iter_seeds)
+ def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
+ raise NotImplementedError()
-
+ def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
+ raise NotImplementedError()
diff --git a/modules/sd_samplers_compvis.py b/modules/sd_samplers_compvis.py new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/modules/sd_samplers_compvis.py diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 5613b8c1..8a8c87e0 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -1,8 +1,9 @@ import torch
import inspect
import k_diffusion.sampling
-from modules import sd_samplers_common, sd_samplers_extra
-from modules.sd_samplers_cfg_denoiser import CFGDenoiser
+from modules import sd_samplers_common, sd_samplers_extra, sd_samplers_cfg_denoiser
+from modules.sd_samplers_cfg_denoiser import CFGDenoiser # noqa: F401
+from modules.script_callbacks import ExtraNoiseParams, extra_noise_callback
from modules.shared import opts
import modules.shared as shared
@@ -16,19 +17,25 @@ samplers_k_diffusion = [ ('Euler', 'sample_euler', ['k_euler'], {}),
('LMS', 'sample_lms', ['k_lms'], {}),
('Heun', 'sample_heun', ['k_heun'], {"second_order": True}),
- ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True}),
- ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True, "uses_ensd": True}),
+ ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True, "second_order": True}),
+ ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}),
('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {"uses_ensd": True, "second_order": True}),
('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {"second_order": True, "brownian_noise": True}),
('DPM++ 2M SDE', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_ka'], {"brownian_noise": True}),
+ ('DPM++ 2M SDE Heun', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_heun'], {"brownian_noise": True, "solver_type": "heun"}),
+ ('DPM++ 2M SDE Heun Karras', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_heun_ka'], {'scheduler': 'karras', "brownian_noise": True, "solver_type": "heun"}),
+ ('DPM++ 2M SDE Heun Exponential', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_heun_exp'], {'scheduler': 'exponential', "brownian_noise": True, "solver_type": "heun"}),
+ ('DPM++ 3M SDE', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde'], {'discard_next_to_last_sigma': True, "brownian_noise": True}),
+ ('DPM++ 3M SDE Karras', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "brownian_noise": True}),
+ ('DPM++ 3M SDE Exponential', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde_exp'], {'scheduler': 'exponential', 'discard_next_to_last_sigma': True, "brownian_noise": True}),
('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {"uses_ensd": True}),
('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {"uses_ensd": True}),
('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}),
('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}),
('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras', "uses_ensd": True, "second_order": True}),
- ('Restart', sd_samplers_extra.restart_sampler, ['restart'], {'scheduler': 'karras'}),
+ ('Restart', sd_samplers_extra.restart_sampler, ['restart'], {'scheduler': 'karras', "second_order": True}),
]
@@ -42,6 +49,12 @@ sampler_extra_params = { 'sample_euler': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
'sample_heun': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
'sample_dpm_2': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
+ 'sample_dpm_fast': ['s_noise'],
+ 'sample_dpm_2_ancestral': ['s_noise'],
+ 'sample_dpmpp_2s_ancestral': ['s_noise'],
+ 'sample_dpmpp_sde': ['s_noise'],
+ 'sample_dpmpp_2m_sde': ['s_noise'],
+ 'sample_dpmpp_3m_sde': ['s_noise'],
}
k_diffusion_samplers_map = {x.name: x for x in samplers_data_k_diffusion}
@@ -53,17 +66,27 @@ k_diffusion_scheduler = { }
-class KDiffusionSampler(sd_samplers_common.Sampler):
- def __init__(self, funcname, sd_model):
+class CFGDenoiserKDiffusion(sd_samplers_cfg_denoiser.CFGDenoiser):
+ @property
+ def inner_model(self):
+ if self.model_wrap is None:
+ denoiser = k_diffusion.external.CompVisVDenoiser if shared.sd_model.parameterization == "v" else k_diffusion.external.CompVisDenoiser
+ self.model_wrap = denoiser(shared.sd_model, quantize=shared.opts.enable_quantization)
+
+ return self.model_wrap
+
+class KDiffusionSampler(sd_samplers_common.Sampler):
+ def __init__(self, funcname, sd_model, options=None):
super().__init__(funcname)
self.extra_params = sampler_extra_params.get(funcname, [])
+
+ self.options = options or {}
self.func = funcname if callable(funcname) else getattr(k_diffusion.sampling, self.funcname)
- denoiser = k_diffusion.external.CompVisVDenoiser if sd_model.parameterization == "v" else k_diffusion.external.CompVisDenoiser
- self.model_wrap = denoiser(sd_model, quantize=shared.opts.enable_quantization)
- self.model_wrap_cfg = CFGDenoiser(self.model_wrap, self)
+ self.model_wrap_cfg = CFGDenoiserKDiffusion(self)
+ self.model_wrap = self.model_wrap_cfg.inner_model
def get_sigmas(self, p, steps):
discard_next_to_last_sigma = self.config is not None and self.config.options.get('discard_next_to_last_sigma', False)
@@ -123,6 +146,13 @@ class KDiffusionSampler(sd_samplers_common.Sampler): xi = x + noise * sigma_sched[0]
+ if opts.img2img_extra_noise > 0:
+ p.extra_generation_params["Extra noise"] = opts.img2img_extra_noise
+ extra_noise_params = ExtraNoiseParams(noise, x, xi)
+ extra_noise_callback(extra_noise_params)
+ noise = extra_noise_params.noise
+ xi += noise * opts.img2img_extra_noise
+
extra_params_kwargs = self.initialize(p)
parameters = inspect.signature(self.func).parameters
@@ -142,9 +172,12 @@ class KDiffusionSampler(sd_samplers_common.Sampler): noise_sampler = self.create_noise_sampler(x, sigmas, p)
extra_params_kwargs['noise_sampler'] = noise_sampler
+ if self.config.options.get('solver_type', None) == 'heun':
+ extra_params_kwargs['solver_type'] = 'heun'
+
self.model_wrap_cfg.init_latent = x
self.last_latent = x
- extra_args = {
+ self.sampler_extra_args = {
'cond': conditioning,
'image_cond': image_conditioning,
'uncond': unconditional_conditioning,
@@ -152,7 +185,7 @@ class KDiffusionSampler(sd_samplers_common.Sampler): 's_min_uncond': self.s_min_uncond
}
- samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
+ samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
if self.model_wrap_cfg.padded_cond_uncond:
p.extra_generation_params["Pad conds"] = True
@@ -164,7 +197,11 @@ class KDiffusionSampler(sd_samplers_common.Sampler): sigmas = self.get_sigmas(p, steps)
- x = x * sigmas[0]
+ if opts.sgm_noise_multiplier:
+ p.extra_generation_params["SGM noise multiplier"] = True
+ x = x * torch.sqrt(1.0 + sigmas[0] ** 2.0)
+ else:
+ x = x * sigmas[0]
extra_params_kwargs = self.initialize(p)
parameters = inspect.signature(self.func).parameters
@@ -183,14 +220,19 @@ class KDiffusionSampler(sd_samplers_common.Sampler): noise_sampler = self.create_noise_sampler(x, sigmas, p)
extra_params_kwargs['noise_sampler'] = noise_sampler
+ if self.config.options.get('solver_type', None) == 'heun':
+ extra_params_kwargs['solver_type'] = 'heun'
+
self.last_latent = x
- samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
+ self.sampler_extra_args = {
'cond': conditioning,
'image_cond': image_conditioning,
'uncond': unconditional_conditioning,
'cond_scale': p.cfg_scale,
's_min_uncond': self.s_min_uncond
- }, disable=False, callback=self.callback_state, **extra_params_kwargs))
+ }
+
+ samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
if self.model_wrap_cfg.padded_cond_uncond:
p.extra_generation_params["Pad conds"] = True
diff --git a/modules/sd_samplers_timesteps.py b/modules/sd_samplers_timesteps.py index f61799a8..b17a8f93 100644 --- a/modules/sd_samplers_timesteps.py +++ b/modules/sd_samplers_timesteps.py @@ -3,6 +3,7 @@ import inspect import sys
from modules import devices, sd_samplers_common, sd_samplers_timesteps_impl
from modules.sd_samplers_cfg_denoiser import CFGDenoiser
+from modules.script_callbacks import ExtraNoiseParams, extra_noise_callback
from modules.shared import opts
import modules.shared as shared
@@ -45,22 +46,30 @@ class CompVisTimestepsVDenoiser(torch.nn.Module): class CFGDenoiserTimesteps(CFGDenoiser):
- def __init__(self, model, sampler):
- super().__init__(model, sampler)
+ def __init__(self, sampler):
+ super().__init__(sampler)
- self.alphas = model.inner_model.alphas_cumprod
+ self.alphas = shared.sd_model.alphas_cumprod
+ self.mask_before_denoising = True
def get_pred_x0(self, x_in, x_out, sigma):
- ts = int(sigma.item())
+ ts = sigma.to(dtype=int)
- s_in = x_in.new_ones([x_in.shape[0]])
- a_t = self.alphas[ts].item() * s_in
+ a_t = self.alphas[ts][:, None, None, None]
sqrt_one_minus_at = (1 - a_t).sqrt()
pred_x0 = (x_in - sqrt_one_minus_at * x_out) / a_t.sqrt()
return pred_x0
+ @property
+ def inner_model(self):
+ if self.model_wrap is None:
+ denoiser = CompVisTimestepsVDenoiser if shared.sd_model.parameterization == "v" else CompVisTimestepsDenoiser
+ self.model_wrap = denoiser(shared.sd_model)
+
+ return self.model_wrap
+
class CompVisSampler(sd_samplers_common.Sampler):
def __init__(self, funcname, sd_model):
@@ -68,10 +77,9 @@ class CompVisSampler(sd_samplers_common.Sampler): self.eta_option_field = 'eta_ddim'
self.eta_infotext_field = 'Eta DDIM'
+ self.eta_default = 0.0
- denoiser = CompVisTimestepsVDenoiser if sd_model.parameterization == "v" else CompVisTimestepsDenoiser
- self.model_wrap = denoiser(sd_model)
- self.model_wrap_cfg = CFGDenoiserTimesteps(self.model_wrap, self)
+ self.model_wrap_cfg = CFGDenoiserTimesteps(self)
def get_timesteps(self, p, steps):
discard_next_to_last_sigma = self.config is not None and self.config.options.get('discard_next_to_last_sigma', False)
@@ -97,6 +105,13 @@ class CompVisSampler(sd_samplers_common.Sampler): xi = x * sqrt_alpha_cumprod + noise * sqrt_one_minus_alpha_cumprod
+ if opts.img2img_extra_noise > 0:
+ p.extra_generation_params["Extra noise"] = opts.img2img_extra_noise
+ extra_noise_params = ExtraNoiseParams(noise, x, xi)
+ extra_noise_callback(extra_noise_params)
+ noise = extra_noise_params.noise
+ xi += noise * opts.img2img_extra_noise * sqrt_alpha_cumprod
+
extra_params_kwargs = self.initialize(p)
parameters = inspect.signature(self.func).parameters
@@ -107,7 +122,7 @@ class CompVisSampler(sd_samplers_common.Sampler): self.model_wrap_cfg.init_latent = x
self.last_latent = x
- extra_args = {
+ self.sampler_extra_args = {
'cond': conditioning,
'image_cond': image_conditioning,
'uncond': unconditional_conditioning,
@@ -115,7 +130,7 @@ class CompVisSampler(sd_samplers_common.Sampler): 's_min_uncond': self.s_min_uncond
}
- samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
+ samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
if self.model_wrap_cfg.padded_cond_uncond:
p.extra_generation_params["Pad conds"] = True
@@ -133,13 +148,14 @@ class CompVisSampler(sd_samplers_common.Sampler): extra_params_kwargs['timesteps'] = timesteps
self.last_latent = x
- samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
+ self.sampler_extra_args = {
'cond': conditioning,
'image_cond': image_conditioning,
'uncond': unconditional_conditioning,
'cond_scale': p.cfg_scale,
's_min_uncond': self.s_min_uncond
- }, disable=False, callback=self.callback_state, **extra_params_kwargs))
+ }
+ samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
if self.model_wrap_cfg.padded_cond_uncond:
p.extra_generation_params["Pad conds"] = True
diff --git a/modules/sd_samplers_timesteps_impl.py b/modules/sd_samplers_timesteps_impl.py index 48d7e649..a72daafd 100644 --- a/modules/sd_samplers_timesteps_impl.py +++ b/modules/sd_samplers_timesteps_impl.py @@ -11,21 +11,22 @@ from modules.models.diffusion.uni_pc import uni_pc def ddim(model, x, timesteps, extra_args=None, callback=None, disable=None, eta=0.0):
alphas_cumprod = model.inner_model.inner_model.alphas_cumprod
alphas = alphas_cumprod[timesteps]
- alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64)
+ alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64 if x.device.type != 'mps' else torch.float32)
sqrt_one_minus_alphas = torch.sqrt(1 - alphas)
sigmas = eta * np.sqrt((1 - alphas_prev.cpu().numpy()) / (1 - alphas.cpu()) * (1 - alphas.cpu() / alphas_prev.cpu().numpy()))
extra_args = {} if extra_args is None else extra_args
- s_in = x.new_ones([x.shape[0]])
+ s_in = x.new_ones((x.shape[0]))
+ s_x = x.new_ones((x.shape[0], 1, 1, 1))
for i in tqdm.trange(len(timesteps) - 1, disable=disable):
index = len(timesteps) - 1 - i
e_t = model(x, timesteps[index].item() * s_in, **extra_args)
- a_t = alphas[index].item() * s_in
- a_prev = alphas_prev[index].item() * s_in
- sigma_t = sigmas[index].item() * s_in
- sqrt_one_minus_at = sqrt_one_minus_alphas[index].item() * s_in
+ a_t = alphas[index].item() * s_x
+ a_prev = alphas_prev[index].item() * s_x
+ sigma_t = sigmas[index].item() * s_x
+ sqrt_one_minus_at = sqrt_one_minus_alphas[index].item() * s_x
pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
dir_xt = (1. - a_prev - sigma_t ** 2).sqrt() * e_t
@@ -42,18 +43,19 @@ def ddim(model, x, timesteps, extra_args=None, callback=None, disable=None, eta= def plms(model, x, timesteps, extra_args=None, callback=None, disable=None):
alphas_cumprod = model.inner_model.inner_model.alphas_cumprod
alphas = alphas_cumprod[timesteps]
- alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64)
+ alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64 if x.device.type != 'mps' else torch.float32)
sqrt_one_minus_alphas = torch.sqrt(1 - alphas)
extra_args = {} if extra_args is None else extra_args
s_in = x.new_ones([x.shape[0]])
+ s_x = x.new_ones((x.shape[0], 1, 1, 1))
old_eps = []
def get_x_prev_and_pred_x0(e_t, index):
# select parameters corresponding to the currently considered timestep
- a_t = alphas[index].item() * s_in
- a_prev = alphas_prev[index].item() * s_in
- sqrt_one_minus_at = sqrt_one_minus_alphas[index].item() * s_in
+ a_t = alphas[index].item() * s_x
+ a_prev = alphas_prev[index].item() * s_x
+ sqrt_one_minus_at = sqrt_one_minus_alphas[index].item() * s_x
# current prediction for x_0
pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
diff --git a/modules/sd_unet.py b/modules/sd_unet.py index 6d708ad2..6a7bc9e2 100644 --- a/modules/sd_unet.py +++ b/modules/sd_unet.py @@ -1,11 +1,11 @@ import torch.nn
-import ldm.modules.diffusionmodules.openaimodel
from modules import script_callbacks, shared, devices
unet_options = []
current_unet_option = None
current_unet = None
+original_forward = None
def list_unets():
@@ -47,7 +47,7 @@ def apply_unet(option=None): if current_unet_option is None:
current_unet = None
- if not (shared.cmd_opts.lowvram or shared.cmd_opts.medvram):
+ if not shared.sd_model.lowvram:
shared.sd_model.model.diffusion_model.to(devices.device)
return
@@ -88,5 +88,5 @@ def UNetModel_forward(self, x, timesteps=None, context=None, *args, **kwargs): if current_unet is not None:
return current_unet.forward(x, timesteps, context, *args, **kwargs)
- return ldm.modules.diffusionmodules.openaimodel.copy_of_UNetModel_forward_for_webui(self, x, timesteps, context, *args, **kwargs)
+ return original_forward(self, x, timesteps, context, *args, **kwargs)
diff --git a/modules/sd_vae.py b/modules/sd_vae.py index 1db01992..31306d8b 100644 --- a/modules/sd_vae.py +++ b/modules/sd_vae.py @@ -31,7 +31,9 @@ def get_loaded_vae_hash(): if loaded_vae_file is None: return None - return hashes.sha256(loaded_vae_file, 'vae')[0:10] + sha256 = hashes.sha256(loaded_vae_file, 'vae') + + return sha256[0:10] if sha256 else None def get_base_vae(model): @@ -68,7 +70,6 @@ def get_filename(filepath): def refresh_vae_list(): - global vae_dict vae_dict.clear() paths = [ @@ -102,7 +103,7 @@ def refresh_vae_list(): name = get_filename(filepath) vae_dict[name] = filepath - vae_dict = dict(sorted(vae_dict.items(), key=lambda item: shared.natural_sort_key(item[0]))) + vae_dict.update(dict(sorted(vae_dict.items(), key=lambda item: shared.natural_sort_key(item[0])))) def find_vae_near_checkpoint(checkpoint_file): @@ -158,7 +159,7 @@ def resolve_vae_from_user_metadata(checkpoint_file) -> VaeResolution: def resolve_vae_near_checkpoint(checkpoint_file) -> VaeResolution: vae_near_checkpoint = find_vae_near_checkpoint(checkpoint_file) - if vae_near_checkpoint is not None and (shared.opts.sd_vae_as_default or is_automatic): + if vae_near_checkpoint is not None and (not shared.opts.sd_vae_overrides_per_model_preferences or is_automatic()): return VaeResolution(vae_near_checkpoint, 'found near the checkpoint') return VaeResolution(resolved=False) @@ -191,7 +192,7 @@ def load_vae_dict(filename, map_location): def load_vae(model, vae_file=None, vae_source="from unknown source"): - global vae_dict, loaded_vae_file + global vae_dict, base_vae, loaded_vae_file # save_settings = False cache_enabled = shared.opts.sd_vae_checkpoint_cache > 0 @@ -229,6 +230,8 @@ def load_vae(model, vae_file=None, vae_source="from unknown source"): restore_base_vae(model) loaded_vae_file = vae_file + model.base_vae = base_vae + model.loaded_vae_file = loaded_vae_file # don't call this from outside @@ -260,7 +263,7 @@ def reload_vae_weights(sd_model=None, vae_file=unspecified): if loaded_vae_file == vae_file: return - if shared.cmd_opts.lowvram or shared.cmd_opts.medvram: + if sd_model.lowvram: lowvram.send_everything_to_cpu() else: sd_model.to(devices.cpu) @@ -272,7 +275,7 @@ def reload_vae_weights(sd_model=None, vae_file=unspecified): sd_hijack.model_hijack.hijack(sd_model) script_callbacks.model_loaded_callback(sd_model) - if not shared.cmd_opts.lowvram and not shared.cmd_opts.medvram: + if not sd_model.lowvram: sd_model.to(devices.device) print("VAE weights loaded.") diff --git a/modules/shared.py b/modules/shared.py index d9d01484..63661939 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -2,16 +2,15 @@ import sys import gradio as gr
-from modules import shared_cmd_options, shared_gradio_themes, options, shared_items
+from modules import shared_cmd_options, shared_gradio_themes, options, shared_items, sd_models_types
from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir # noqa: F401
-from ldm.models.diffusion.ddpm import LatentDiffusion
from modules import util
cmd_opts = shared_cmd_options.cmd_opts
parser = shared_cmd_options.parser
-batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)
-parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
+batch_cond_uncond = True # old field, unused now in favor of shared.opts.batch_cond_uncond
+parallel_processing_allowed = True
styles_filename = cmd_opts.styles_file
config_filename = cmd_opts.ui_settings_file
hide_dirs = {"visible": not cmd_opts.hide_ui_dir_config}
@@ -40,7 +39,7 @@ options_templates = None opts = None
restricted_opts = None
-sd_model: LatentDiffusion = None
+sd_model: sd_models_types.WebuiSdModel = None
settings_components = None
"""assinged from ui.py, a mapping on setting names to gradio components repsponsible for those settings"""
diff --git a/modules/shared_cmd_options.py b/modules/shared_cmd_options.py index af24938b..c9626667 100644 --- a/modules/shared_cmd_options.py +++ b/modules/shared_cmd_options.py @@ -14,5 +14,5 @@ if os.environ.get('IGNORE_CMD_ARGS_ERRORS', None) is None: else:
cmd_opts, _ = parser.parse_known_args()
-
-cmd_opts.disable_extension_access = (cmd_opts.share or cmd_opts.listen or cmd_opts.server_name) and not cmd_opts.enable_insecure_extension_access
+cmd_opts.webui_is_non_local = any([cmd_opts.share, cmd_opts.listen, cmd_opts.ngrok, cmd_opts.server_name])
+cmd_opts.disable_extension_access = cmd_opts.webui_is_non_local and not cmd_opts.enable_insecure_extension_access
diff --git a/modules/shared_gradio_themes.py b/modules/shared_gradio_themes.py index 485e89d5..822db0a9 100644 --- a/modules/shared_gradio_themes.py +++ b/modules/shared_gradio_themes.py @@ -36,7 +36,8 @@ gradio_hf_hub_themes = [ "step-3-profit/Midnight-Deep",
"Taithrah/Minimal",
"ysharma/huggingface",
- "ysharma/steampunk"
+ "ysharma/steampunk",
+ "NoCrypt/miku"
]
diff --git a/modules/shared_items.py b/modules/shared_items.py index e4ec40a8..5024b426 100644 --- a/modules/shared_items.py +++ b/modules/shared_items.py @@ -44,9 +44,9 @@ def refresh_unet_list(): modules.sd_unet.list_unets()
-def list_checkpoint_tiles():
+def list_checkpoint_tiles(use_short=False):
import modules.sd_models
- return modules.sd_models.checkpoint_tiles()
+ return modules.sd_models.checkpoint_tiles(use_short)
def refresh_checkpoints():
@@ -67,12 +67,15 @@ def reload_hypernetworks(): ui_reorder_categories_builtin_items = [
+ "prompt",
+ "image",
"inpaint",
"sampler",
+ "accordions",
"checkboxes",
- "hires_fix",
"dimensions",
"cfg",
+ "denoising",
"seed",
"batch",
"override_settings",
@@ -86,7 +89,7 @@ def ui_reorder_categories(): sections = {}
for script in scripts.scripts_txt2img.scripts + scripts.scripts_img2img.scripts:
- if isinstance(script.section, str):
+ if isinstance(script.section, str) and script.section not in ui_reorder_categories_builtin_items:
sections[script.section] = 1
yield from sections
diff --git a/modules/shared_options.py b/modules/shared_options.py index 9ae51f18..9bcd7914 100644 --- a/modules/shared_options.py +++ b/modules/shared_options.py @@ -26,7 +26,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "samples_format": OptionInfo('png', 'File format for images'),
"samples_filename_pattern": OptionInfo("", "Images filename pattern", component_args=hide_dirs).link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"),
"save_images_add_number": OptionInfo(True, "Add number to filename when saving", component_args=hide_dirs),
-
+ "save_images_replace_action": OptionInfo("Replace", "Saving the image to an existing file", gr.Radio, {"choices": ["Replace", "Add number suffix"], **hide_dirs}),
"grid_save": OptionInfo(True, "Always save all generated image grids"),
"grid_format": OptionInfo('png', 'File format for grids'),
"grid_extended_filename": OptionInfo(False, "Add extended info (seed, prompt) to filename when saving grid"),
@@ -62,6 +62,9 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "clean_temp_dir_at_start": OptionInfo(False, "Cleanup non-default temporary directory when starting webui"),
"save_incomplete_images": OptionInfo(False, "Save incomplete images").info("save images that has been interrupted in mid-generation; even if not saved, they will still show up in webui output."),
+
+ "notification_audio": OptionInfo(True, "Play notification sound after image generation").info("notification.mp3 should be present in the root directory").needs_reload_ui(),
+ "notification_volume": OptionInfo(100, "Notification sound volume", gr.Slider, {"minimum": 0, "maximum": 100, "step": 1}).info("in %"),
}))
options_templates.update(options_section(('saving-paths', "Paths for saving"), {
@@ -100,6 +103,7 @@ options_templates.update(options_section(('face-restoration', "Face restoration" options_templates.update(options_section(('system', "System"), {
"auto_launch_browser": OptionInfo("Local", "Automatically open webui in browser on startup", gr.Radio, lambda: {"choices": ["Disable", "Local", "Remote"]}),
+ "enable_console_prompts": OptionInfo(shared.cmd_opts.enable_console_prompts, "Print prompts to console when generating with txt2img and img2img."),
"show_warnings": OptionInfo(False, "Show warnings in console.").needs_reload_ui(),
"show_gradio_deprecation_warnings": OptionInfo(True, "Show gradio deprecation warnings in console.").needs_reload_ui(),
"memmon_poll_rate": OptionInfo(8, "VRAM usage polls per second during generation.", gr.Slider, {"minimum": 0, "maximum": 40, "step": 1}).info("0 = disable"),
@@ -109,6 +113,13 @@ options_templates.update(options_section(('system', "System"), { "list_hidden_files": OptionInfo(True, "Load models/files in hidden directories").info("directory is hidden if its name starts with \".\""),
"disable_mmap_load_safetensors": OptionInfo(False, "Disable memmapping for loading .safetensors files.").info("fixes very slow loading speed in some cases"),
"hide_ldm_prints": OptionInfo(True, "Prevent Stability-AI's ldm/sgm modules from printing noise to console."),
+ "dump_stacks_on_signal": OptionInfo(False, "Print stack traces before exiting the program with ctrl+c."),
+}))
+
+options_templates.update(options_section(('API', "API"), {
+ "api_enable_requests": OptionInfo(True, "Allow http:// and https:// URLs for input images in API", restrict_api=True),
+ "api_forbid_local_requests": OptionInfo(True, "Forbid URLs to local resources", restrict_api=True),
+ "api_useragent": OptionInfo("", "User agent for requests", restrict_api=True),
}))
options_templates.update(options_section(('training', "Training"), {
@@ -127,7 +138,7 @@ options_templates.update(options_section(('training', "Training"), { }))
options_templates.update(options_section(('sd', "Stable Diffusion"), {
- "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": shared_items.list_checkpoint_tiles()}, refresh=shared_items.refresh_checkpoints, infotext='Model hash'),
+ "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": shared_items.list_checkpoint_tiles(shared.opts.sd_checkpoint_dropdown_use_short)}, refresh=shared_items.refresh_checkpoints, infotext='Model hash'),
"sd_checkpoints_limit": OptionInfo(1, "Maximum number of checkpoints loaded at the same time", gr.Slider, {"minimum": 1, "maximum": 10, "step": 1}),
"sd_checkpoints_keep_in_cpu": OptionInfo(True, "Only keep one model on device").info("will keep models other than the currently used one in RAM rather than VRAM"),
"sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}).info("obsolete; set to 0 and use the two settings above instead"),
@@ -138,8 +149,9 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "comma_padding_backtrack": OptionInfo(20, "Prompt word wrap length limit", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1}).info("in tokens - for texts shorter than specified, if they don't fit into 75 token limit, move them to the next 75 token chunk"),
"CLIP_stop_at_last_layers": OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}, infotext="Clip skip").link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#clip-skip").info("ignore last layers of CLIP network; 1 ignores none, 2 ignores one layer"),
"upcast_attn": OptionInfo(False, "Upcast cross attention layer to float32"),
- "randn_source": OptionInfo("GPU", "Random number generator source.", gr.Radio, {"choices": ["GPU", "CPU", "NV"]}).info("changes seeds drastically; use CPU to produce the same picture across different videocard vendors; use NV to produce same picture as on NVidia videocards"),
+ "randn_source": OptionInfo("GPU", "Random number generator source.", gr.Radio, {"choices": ["GPU", "CPU", "NV"]}, infotext="RNG").info("changes seeds drastically; use CPU to produce the same picture across different videocard vendors; use NV to produce same picture as on NVidia videocards"),
"tiling": OptionInfo(False, "Tiling", infotext='Tiling').info("produce a tileable picture"),
+ "hires_fix_refiner_pass": OptionInfo("second pass", "Hires fix: which pass to enable refiner for", gr.Radio, {"choices": ["first pass", "second pass", "both passes"]}, infotext="Hires refiner"),
}))
options_templates.update(options_section(('sdxl', "Stable Diffusion XL"), {
@@ -166,7 +178,8 @@ For img2img, VAE is used to process user's input image before the sampling, and options_templates.update(options_section(('img2img', "img2img"), {
"inpainting_mask_weight": OptionInfo(1.0, "Inpainting conditioning mask strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Conditional mask weight'),
- "initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.5, "maximum": 1.5, "step": 0.01}, infotext='Noise multiplier'),
+ "initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.0, "maximum": 1.5, "step": 0.001}, infotext='Noise multiplier'),
+ "img2img_extra_noise": OptionInfo(0.0, "Extra noise multiplier for img2img and hires fix", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Extra noise').info("0 = disabled (default); should be lower than denoising strength"),
"img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."),
"img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies.").info("normally you'd do less with less denoising"),
"img2img_background_color": OptionInfo("#ffffff", "With img2img, fill transparent parts of the input image with this color.", ui_components.FormColorPicker, {}),
@@ -176,6 +189,7 @@ options_templates.update(options_section(('img2img', "img2img"), { "img2img_inpaint_sketch_default_brush_color": OptionInfo("#ffffff", "Inpaint sketch initial brush color", ui_components.FormColorPicker, {}).info("default brush color of img2img inpaint sketch").needs_reload_ui(),
"return_mask": OptionInfo(False, "For inpainting, include the greyscale mask in results for web"),
"return_mask_composite": OptionInfo(False, "For inpainting, include masked composite in results for web"),
+ "img2img_batch_show_results_limit": OptionInfo(32, "Show the first N batch img2img results in UI", gr.Slider, {"minimum": -1, "maximum": 1000, "step": 1}).info('0: disable, -1: show all images. Too many images can cause lag'),
}))
options_templates.update(options_section(('optimizations', "Optimizations"), {
@@ -185,7 +199,8 @@ options_templates.update(options_section(('optimizations', "Optimizations"), { "token_merging_ratio_img2img": OptionInfo(0.0, "Token merging ratio for img2img", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).info("only applies if non-zero and overrides above"),
"token_merging_ratio_hr": OptionInfo(0.0, "Token merging ratio for high-res pass", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio hr').info("only applies if non-zero and overrides above"),
"pad_cond_uncond": OptionInfo(False, "Pad prompt/negative prompt to be same length", infotext='Pad conds').info("improves performance when prompt and negative prompt have different lengths; changes seeds"),
- "persistent_cond_cache": OptionInfo(True, "Persistent cond cache").info("Do not recalculate conds from prompts if prompts have not changed since previous calculation"),
+ "persistent_cond_cache": OptionInfo(True, "Persistent cond cache").info("do not recalculate conds from prompts if prompts have not changed since previous calculation"),
+ "batch_cond_uncond": OptionInfo(True, "Batch cond/uncond").info("do both conditional and unconditional denoising in one batch; uses a bit more VRAM during sampling, but improves speed; previously this was controlled by --always-batch-cond-uncond comandline argument"),
}))
options_templates.update(options_section(('compatibility', "Compatibility"), {
@@ -195,6 +210,7 @@ options_templates.update(options_section(('compatibility', "Compatibility"), { "use_old_hires_fix_width_height": OptionInfo(False, "For hires fix, use width/height sliders to set final resolution rather than first pass (disables Upscale by, Resize width/height to)."),
"dont_fix_second_order_samplers_schedule": OptionInfo(False, "Do not fix prompt schedule for second order samplers."),
"hires_fix_use_firstpass_conds": OptionInfo(False, "For hires fix, calculate conds of second pass using extra networks of first pass."),
+ "use_old_scheduling": OptionInfo(False, "Use old prompt editing timelines.", infotext="Old prompt editing timelines").info("For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps"),
}))
options_templates.update(options_section(('interrogate', "Interrogate"), {
@@ -220,6 +236,8 @@ options_templates.update(options_section(('extra_networks', "Extra Networks"), { "extra_networks_card_height": OptionInfo(0, "Card height for Extra Networks").info("in pixels"),
"extra_networks_card_text_scale": OptionInfo(1.0, "Card text scale", gr.Slider, {"minimum": 0.0, "maximum": 2.0, "step": 0.01}).info("1 = original size"),
"extra_networks_card_show_desc": OptionInfo(True, "Show description on card"),
+ "extra_networks_card_order_field": OptionInfo("Path", "Default order field for Extra Networks cards", gr.Dropdown, {"choices": ['Path', 'Name', 'Date Created', 'Date Modified']}).needs_reload_ui(),
+ "extra_networks_card_order": OptionInfo("Ascending", "Default order for Extra Networks cards", gr.Dropdown, {"choices": ['Ascending', 'Descending']}).needs_reload_ui(),
"extra_networks_add_text_separator": OptionInfo(" ", "Extra networks separator").info("extra text to add before <...> when adding extra network to prompt"),
"ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order").needs_reload_ui(),
"textual_inversion_print_at_load": OptionInfo(False, "Print a list of Textual Inversion embeddings when loading model"),
@@ -231,6 +249,7 @@ options_templates.update(options_section(('ui', "User interface"), { "localization": OptionInfo("None", "Localization", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)).needs_reload_ui(),
"gradio_theme": OptionInfo("Default", "Gradio theme", ui_components.DropdownEditable, lambda: {"choices": ["Default"] + shared_gradio_themes.gradio_hf_hub_themes}).info("you can also manually enter any of themes from the <a href='https://huggingface.co/spaces/gradio/theme-gallery'>gallery</a>.").needs_reload_ui(),
"gradio_themes_cache": OptionInfo(True, "Cache gradio themes locally").info("disable to update the selected Gradio theme"),
+ "gallery_height": OptionInfo("", "Gallery height", gr.Textbox).info("an be any valid CSS value").needs_reload_ui(),
"return_grid": OptionInfo(True, "Show grid in results for web"),
"do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),
"send_seed": OptionInfo(True, "Send seed when sending prompt or image to other interface"),
@@ -244,15 +263,20 @@ options_templates.update(options_section(('ui', "User interface"), { "dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row").needs_reload_ui(),
"keyedit_precision_attention": OptionInfo(0.1, "Ctrl+up/down precision when editing (attention:1.1)", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
"keyedit_precision_extra": OptionInfo(0.05, "Ctrl+up/down precision when editing <extra networks:0.9>", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
- "keyedit_delimiters": OptionInfo(".,\\/!?%^*;:{}=`~()", "Ctrl+up/down word delimiters"),
+ "keyedit_delimiters": OptionInfo(r".,\/!?%^*;:{}=`~() ", "Ctrl+up/down word delimiters"),
+ "keyedit_delimiters_whitespace": OptionInfo(["Tab", "Carriage Return", "Line Feed"], "Ctrl+up/down whitespace delimiters", gr.CheckboxGroup, lambda: {"choices": ["Tab", "Carriage Return", "Line Feed"]}),
"keyedit_move": OptionInfo(True, "Alt+left/right moves prompt elements"),
"quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that appear at the top of page rather than in settings tab").needs_reload_ui(),
"ui_tab_order": OptionInfo([], "UI tab order", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
"hidden_tabs": OptionInfo([], "Hidden UI tabs", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
"ui_reorder_list": OptionInfo([], "txt2img/img2img UI item order", ui_components.DropdownMulti, lambda: {"choices": list(shared_items.ui_reorder_categories())}).info("selected items appear first").needs_reload_ui(),
+ "sd_checkpoint_dropdown_use_short": OptionInfo(False, "Checkpoint dropdown: use filenames without paths").info("models in subdirectories like photo/sd15.ckpt will be listed as just sd15.ckpt"),
"hires_fix_show_sampler": OptionInfo(False, "Hires fix: show hires checkpoint and sampler selection").needs_reload_ui(),
"hires_fix_show_prompts": OptionInfo(False, "Hires fix: show hires prompt and negative prompt").needs_reload_ui(),
"disable_token_counters": OptionInfo(False, "Disable prompt token counters").needs_reload_ui(),
+ "txt2img_settings_accordion": OptionInfo(False, "Settings in txt2img hidden under Accordion").needs_reload_ui(),
+ "img2img_settings_accordion": OptionInfo(False, "Settings in img2img hidden under Accordion").needs_reload_ui(),
+ "compact_prompt_box": OptionInfo(False, "Compact prompt layout").info("puts prompt and negative prompt inside the Generate tab, leaving more vertical space for the image on the right").needs_reload_ui(),
}))
@@ -278,25 +302,28 @@ options_templates.update(options_section(('ui', "Live previews"), { "show_progress_grid": OptionInfo(True, "Show previews of all images generated in a batch as a grid"),
"show_progress_every_n_steps": OptionInfo(10, "Live preview display period", gr.Slider, {"minimum": -1, "maximum": 32, "step": 1}).info("in sampling steps - show new live preview image every N sampling steps; -1 = only show after completion of batch"),
"show_progress_type": OptionInfo("Approx NN", "Live preview method", gr.Radio, {"choices": ["Full", "Approx NN", "Approx cheap", "TAESD"]}).info("Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise"),
+ "live_preview_allow_lowvram_full": OptionInfo(False, "Allow Full live preview method with lowvram/medvram").info("If not, Approx NN will be used instead; Full live preview method is very detrimental to speed if lowvram/medvram optimizations are enabled"),
"live_preview_content": OptionInfo("Prompt", "Live preview subject", gr.Radio, {"choices": ["Combined", "Prompt", "Negative prompt"]}),
"live_preview_refresh_period": OptionInfo(1000, "Progressbar and preview update period").info("in milliseconds"),
+ "live_preview_fast_interrupt": OptionInfo(False, "Return image with chosen live preview method on interrupt").info("makes interrupts faster"),
}))
options_templates.update(options_section(('sampler-params', "Sampler parameters"), {
"hide_samplers": OptionInfo([], "Hide samplers in user interface", gr.CheckboxGroup, lambda: {"choices": [x.name for x in shared_items.list_samplers()]}).needs_reload_ui(),
- "eta_ddim": OptionInfo(0.0, "Eta for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta DDIM').info("noise multiplier; higher = more unperdictable results"),
- "eta_ancestral": OptionInfo(1.0, "Eta for ancestral samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta').info("noise multiplier; applies to Euler a and other samplers that have a in them"),
+ "eta_ddim": OptionInfo(0.0, "Eta for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta DDIM').info("noise multiplier; higher = more unpredictable results"),
+ "eta_ancestral": OptionInfo(1.0, "Eta for k-diffusion samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta').info("noise multiplier; currently only applies to ancestral samplers (i.e. Euler a) and SDE samplers"),
"ddim_discretize": OptionInfo('uniform', "img2img DDIM discretize", gr.Radio, {"choices": ['uniform', 'quad']}),
's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 100.0, "step": 0.01}, infotext='Sigma churn').info('amount of stochasticity; only applies to Euler, Heun, and DPM2'),
's_tmin': OptionInfo(0.0, "sigma tmin", gr.Slider, {"minimum": 0.0, "maximum": 10.0, "step": 0.01}, infotext='Sigma tmin').info('enable stochasticity; start value of the sigma range; only applies to Euler, Heun, and DPM2'),
's_tmax': OptionInfo(0.0, "sigma tmax", gr.Slider, {"minimum": 0.0, "maximum": 999.0, "step": 0.01}, infotext='Sigma tmax').info("0 = inf; end value of the sigma range; only applies to Euler, Heun, and DPM2"),
- 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.1, "step": 0.001}, infotext='Sigma noise').info('amount of additional noise to counteract loss of detail during sampling; only applies to Euler, Heun, and DPM2'),
+ 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.1, "step": 0.001}, infotext='Sigma noise').info('amount of additional noise to counteract loss of detail during sampling'),
'k_sched_type': OptionInfo("Automatic", "Scheduler type", gr.Dropdown, {"choices": ["Automatic", "karras", "exponential", "polyexponential"]}, infotext='Schedule type').info("lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below"),
- 'sigma_min': OptionInfo(0.0, "sigma min", gr.Number, infotext='Schedule max sigma').info("0 = default (~0.03); minimum noise strength for k-diffusion noise scheduler"),
- 'sigma_max': OptionInfo(0.0, "sigma max", gr.Number, infotext='Schedule min sigma').info("0 = default (~14.6); maximum noise strength for k-diffusion noise scheduler"),
+ 'sigma_min': OptionInfo(0.0, "sigma min", gr.Number, infotext='Schedule min sigma').info("0 = default (~0.03); minimum noise strength for k-diffusion noise scheduler"),
+ 'sigma_max': OptionInfo(0.0, "sigma max", gr.Number, infotext='Schedule max sigma').info("0 = default (~14.6); maximum noise strength for k-diffusion noise scheduler"),
'rho': OptionInfo(0.0, "rho", gr.Number, infotext='Schedule rho').info("0 = default (7 for karras, 1 for polyexponential); higher values result in a steeper noise schedule (decreases faster)"),
'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}, infotext='ENSD').info("ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images"),
'always_discard_next_to_last_sigma': OptionInfo(False, "Always discard next-to-last sigma", infotext='Discard penultimate sigma').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/6044"),
+ 'sgm_noise_multiplier': OptionInfo(False, "SGM noise multiplier", infotext='SGM noise multplier').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818").info("Match initial noise to official SDXL implementation - only useful for reproducing images"),
'uni_pc_variant': OptionInfo("bh1", "UniPC variant", gr.Radio, {"choices": ["bh1", "bh2", "vary_coeff"]}, infotext='UniPC variant'),
'uni_pc_skip_type': OptionInfo("time_uniform", "UniPC skip type", gr.Radio, {"choices": ["time_uniform", "time_quadratic", "logSNR"]}, infotext='UniPC skip type'),
'uni_pc_order': OptionInfo(3, "UniPC order", gr.Slider, {"minimum": 1, "maximum": 50, "step": 1}, infotext='UniPC order').info("must be < sampling steps"),
@@ -315,4 +342,3 @@ options_templates.update(options_section((None, "Hidden options"), { "restore_config_state_file": OptionInfo("", "Config state file to restore from, under 'config-states/' folder"),
"sd_checkpoint_hash": OptionInfo("", "SHA256 hash of the current checkpoint"),
}))
-
diff --git a/modules/shared_state.py b/modules/shared_state.py index 3dc9c788..a68789cc 100644 --- a/modules/shared_state.py +++ b/modules/shared_state.py @@ -103,6 +103,7 @@ class State: def begin(self, job: str = "(unknown)"):
self.sampling_step = 0
+ self.time_start = time.time()
self.job_count = -1
self.processing_has_refined_job_count = False
self.job_no = 0
@@ -114,7 +115,6 @@ class State: self.skipped = False
self.interrupted = False
self.textinfo = None
- self.time_start = time.time()
self.job = job
devices.torch_gc()
log.info("Starting job %s", job)
@@ -128,7 +128,7 @@ class State: devices.torch_gc()
def set_current_image(self):
- """sets self.current_image from self.current_latent if enough sampling steps have been made after the last call to this"""
+ """if enough sampling steps have been made after the last call to this, sets self.current_image from self.current_latent, and modifies self.id_live_preview accordingly"""
if not shared.parallel_processing_allowed:
return
diff --git a/modules/sub_quadratic_attention.py b/modules/sub_quadratic_attention.py index 497568eb..4cb561ef 100644 --- a/modules/sub_quadratic_attention.py +++ b/modules/sub_quadratic_attention.py @@ -15,7 +15,7 @@ import torch from torch import Tensor from torch.utils.checkpoint import checkpoint import math -from typing import Optional, NamedTuple, List +from typing import Optional, NamedTuple def narrow_trunc( @@ -58,7 +58,7 @@ def _summarize_chunk( scale: float, ) -> AttnChunk: attn_weights = torch.baddbmm( - torch.empty(1, 1, 1, device=query.device, dtype=query.dtype), + torch.zeros(1, 1, 1, device=query.device, dtype=query.dtype), query, key.transpose(1,2), alpha=scale, @@ -97,7 +97,7 @@ def _query_chunk_attention( ) return summarize_chunk(query, key_chunk, value_chunk) - chunks: List[AttnChunk] = [ + chunks: list[AttnChunk] = [ chunk_scanner(chunk) for chunk in torch.arange(0, k_tokens, kv_chunk_size) ] acc_chunk = AttnChunk(*map(torch.stack, zip(*chunks))) @@ -121,7 +121,7 @@ def _get_attention_scores_no_kv_chunking( scale: float, ) -> Tensor: attn_scores = torch.baddbmm( - torch.empty(1, 1, 1, device=query.device, dtype=query.dtype), + torch.zeros(1, 1, 1, device=query.device, dtype=query.dtype), query, key.transpose(1,2), alpha=scale, diff --git a/modules/sysinfo.py b/modules/sysinfo.py index 1d058950..b669edd0 100644 --- a/modules/sysinfo.py +++ b/modules/sysinfo.py @@ -22,7 +22,6 @@ environment_whitelist = { "TORCH_COMMAND",
"REQS_FILE",
"XFORMERS_PACKAGE",
- "GFPGAN_PACKAGE",
"CLIP_PACKAGE",
"OPENCLIP_PACKAGE",
"STABLE_DIFFUSION_REPO",
@@ -82,7 +81,7 @@ def get_dict(): "Data path": paths_internal.data_path,
"Extensions dir": paths_internal.extensions_dir,
"Checksum": checksum_token,
- "Commandline": sys.argv,
+ "Commandline": get_argv(),
"Torch env info": get_torch_sysinfo(),
"Exceptions": errors.get_exceptions(),
"CPU": {
@@ -108,6 +107,22 @@ def get_environment(): return {k: os.environ[k] for k in sorted(os.environ) if k in environment_whitelist}
+def get_argv():
+ res = []
+
+ for v in sys.argv:
+ if shared.cmd_opts.gradio_auth and shared.cmd_opts.gradio_auth == v:
+ res.append("<hidden>")
+ continue
+
+ if shared.cmd_opts.api_auth and shared.cmd_opts.api_auth == v:
+ res.append("<hidden>")
+ continue
+
+ res.append(v)
+
+ return res
+
re_newline = re.compile(r"\r*\n")
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index aa79dc09..04dda585 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -181,40 +181,7 @@ class EmbeddingDatabase: else:
return
-
- # textual inversion embeddings
- if 'string_to_param' in data:
- param_dict = data['string_to_param']
- param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11
- assert len(param_dict) == 1, 'embedding file has multiple terms in it'
- emb = next(iter(param_dict.items()))[1]
- vec = emb.detach().to(devices.device, dtype=torch.float32)
- shape = vec.shape[-1]
- vectors = vec.shape[0]
- elif type(data) == dict and 'clip_g' in data and 'clip_l' in data: # SDXL embedding
- vec = {k: v.detach().to(devices.device, dtype=torch.float32) for k, v in data.items()}
- shape = data['clip_g'].shape[-1] + data['clip_l'].shape[-1]
- vectors = data['clip_g'].shape[0]
- elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor: # diffuser concepts
- assert len(data.keys()) == 1, 'embedding file has multiple terms in it'
-
- emb = next(iter(data.values()))
- if len(emb.shape) == 1:
- emb = emb.unsqueeze(0)
- vec = emb.detach().to(devices.device, dtype=torch.float32)
- shape = vec.shape[-1]
- vectors = vec.shape[0]
- else:
- raise Exception(f"Couldn't identify {filename} as neither textual inversion embedding nor diffuser concept.")
-
- embedding = Embedding(vec, name)
- embedding.step = data.get('step', None)
- embedding.sd_checkpoint = data.get('sd_checkpoint', None)
- embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
- embedding.vectors = vectors
- embedding.shape = shape
- embedding.filename = path
- embedding.set_hash(hashes.sha256(embedding.filename, "textual_inversion/" + name) or '')
+ embedding = create_embedding_from_data(data, name, filename=filename, filepath=path)
if self.expected_shape == -1 or self.expected_shape == embedding.shape:
self.register_embedding(embedding, shared.sd_model)
@@ -313,6 +280,45 @@ def create_embedding(name, num_vectors_per_token, overwrite_old, init_text='*'): return fn
+def create_embedding_from_data(data, name, filename='unknown embedding file', filepath=None):
+ if 'string_to_param' in data: # textual inversion embeddings
+ param_dict = data['string_to_param']
+ param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11
+ assert len(param_dict) == 1, 'embedding file has multiple terms in it'
+ emb = next(iter(param_dict.items()))[1]
+ vec = emb.detach().to(devices.device, dtype=torch.float32)
+ shape = vec.shape[-1]
+ vectors = vec.shape[0]
+ elif type(data) == dict and 'clip_g' in data and 'clip_l' in data: # SDXL embedding
+ vec = {k: v.detach().to(devices.device, dtype=torch.float32) for k, v in data.items()}
+ shape = data['clip_g'].shape[-1] + data['clip_l'].shape[-1]
+ vectors = data['clip_g'].shape[0]
+ elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor: # diffuser concepts
+ assert len(data.keys()) == 1, 'embedding file has multiple terms in it'
+
+ emb = next(iter(data.values()))
+ if len(emb.shape) == 1:
+ emb = emb.unsqueeze(0)
+ vec = emb.detach().to(devices.device, dtype=torch.float32)
+ shape = vec.shape[-1]
+ vectors = vec.shape[0]
+ else:
+ raise Exception(f"Couldn't identify {filename} as neither textual inversion embedding nor diffuser concept.")
+
+ embedding = Embedding(vec, name)
+ embedding.step = data.get('step', None)
+ embedding.sd_checkpoint = data.get('sd_checkpoint', None)
+ embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
+ embedding.vectors = vectors
+ embedding.shape = shape
+
+ if filepath:
+ embedding.filename = filepath
+ embedding.set_hash(hashes.sha256(filepath, "textual_inversion/" + name) or '')
+
+ return embedding
+
+
def write_loss(log_directory, filename, step, epoch_len, values):
if shared.opts.training_write_csv_every == 0:
return
@@ -386,7 +392,7 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat assert log_directory, "Log directory is empty"
-def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_name, preview_cfg_scale, preview_seed, preview_width, preview_height):
from modules import processing
save_embedding_every = save_embedding_every or 0
@@ -590,7 +596,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st p.prompt = preview_prompt
p.negative_prompt = preview_negative_prompt
p.steps = preview_steps
- p.sampler_name = sd_samplers.samplers[preview_sampler_index].name
+ p.sampler_name = sd_samplers.samplers_map[preview_sampler_name.lower()]
p.cfg_scale = preview_cfg_scale
p.seed = preview_seed
p.width = preview_width
diff --git a/modules/txt2img.py b/modules/txt2img.py index 5ea96bba..e4e18ceb 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -3,13 +3,13 @@ from contextlib import closing import modules.scripts
from modules import processing
from modules.generation_parameters_copypaste import create_override_settings_dict
-from modules.shared import opts, cmd_opts
+from modules.shared import opts
import modules.shared as shared
from modules.ui import plaintext_to_html
import gradio as gr
-def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_name: str, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, hr_checkpoint_name: str, hr_sampler_name: str, hr_prompt: str, hr_negative_prompt, override_settings_texts, request: gr.Request, *args):
+def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_name: str, n_iter: int, batch_size: int, cfg_scale: float, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, hr_checkpoint_name: str, hr_sampler_name: str, hr_prompt: str, hr_negative_prompt, override_settings_texts, request: gr.Request, *args):
override_settings = create_override_settings_dict(override_settings_texts)
p = processing.StableDiffusionProcessingTxt2Img(
@@ -19,12 +19,6 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step prompt=prompt,
styles=prompt_styles,
negative_prompt=negative_prompt,
- seed=seed,
- subseed=subseed,
- subseed_strength=subseed_strength,
- seed_resize_from_h=seed_resize_from_h,
- seed_resize_from_w=seed_resize_from_w,
- seed_enable_extras=seed_enable_extras,
sampler_name=sampler_name,
batch_size=batch_size,
n_iter=n_iter,
@@ -51,7 +45,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step p.user = request.username
- if cmd_opts.enable_console_prompts:
+ if shared.opts.enable_console_prompts:
print(f"\ntxt2img: {prompt}", file=shared.progress_print_out)
with closing(p):
diff --git a/modules/ui.py b/modules/ui.py index 05292734..08e0ad77 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1,10 +1,10 @@ import datetime
-import json
import mimetypes
import os
import sys
from functools import reduce
import warnings
+from contextlib import ExitStack
import gradio as gr
import gradio.utils
@@ -13,8 +13,8 @@ from PIL import Image, PngImagePlugin # noqa: F401 from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, wrap_gradio_call
from modules import gradio_extensons # noqa: F401
-from modules import sd_hijack, sd_models, script_callbacks, ui_extensions, deepbooru, extra_networks, ui_common, ui_postprocessing, progress, ui_loadsave, errors, shared_items, ui_settings, timer, sysinfo, ui_checkpoint_merger, ui_prompt_styles, scripts, sd_samplers, processing, ui_extra_networks
-from modules.ui_components import FormRow, FormGroup, ToolButton, FormHTML, InputAccordion
+from modules import sd_hijack, sd_models, script_callbacks, ui_extensions, deepbooru, extra_networks, ui_common, ui_postprocessing, progress, ui_loadsave, shared_items, ui_settings, timer, sysinfo, ui_checkpoint_merger, scripts, sd_samplers, processing, ui_extra_networks, ui_toprow
+from modules.ui_components import FormRow, FormGroup, ToolButton, FormHTML, InputAccordion, ResizeHandleRow
from modules.paths import script_path
from modules.ui_common import create_refresh_button
from modules.ui_gradio_extensions import reload_javascript
@@ -26,7 +26,6 @@ import modules.hypernetworks.ui as hypernetworks_ui import modules.textual_inversion.ui as textual_inversion_ui
import modules.textual_inversion.textual_inversion as textual_inversion
import modules.shared as shared
-import modules.images
from modules import prompt_parser
from modules.sd_hijack import model_hijack
from modules.generation_parameters_copypaste import image_from_url_text
@@ -142,45 +141,6 @@ def interrogate_deepbooru(image): return gr.update() if prompt is None else prompt
-def create_seed_inputs(target_interface):
- with FormRow(elem_id=f"{target_interface}_seed_row", variant="compact"):
- if cmd_opts.use_textbox_seed:
- seed = gr.Textbox(label='Seed', value="", elem_id=f"{target_interface}_seed")
- else:
- seed = gr.Number(label='Seed', value=-1, elem_id=f"{target_interface}_seed", precision=0)
-
- random_seed = ToolButton(random_symbol, elem_id=f"{target_interface}_random_seed", label='Random seed')
- reuse_seed = ToolButton(reuse_symbol, elem_id=f"{target_interface}_reuse_seed", label='Reuse seed')
-
- seed_checkbox = gr.Checkbox(label='Extra', elem_id=f"{target_interface}_subseed_show", value=False)
-
- # Components to show/hide based on the 'Extra' checkbox
- seed_extras = []
-
- with FormRow(visible=False, elem_id=f"{target_interface}_subseed_row") as seed_extra_row_1:
- seed_extras.append(seed_extra_row_1)
- subseed = gr.Number(label='Variation seed', value=-1, elem_id=f"{target_interface}_subseed", precision=0)
- random_subseed = ToolButton(random_symbol, elem_id=f"{target_interface}_random_subseed")
- reuse_subseed = ToolButton(reuse_symbol, elem_id=f"{target_interface}_reuse_subseed")
- subseed_strength = gr.Slider(label='Variation strength', value=0.0, minimum=0, maximum=1, step=0.01, elem_id=f"{target_interface}_subseed_strength")
-
- with FormRow(visible=False) as seed_extra_row_2:
- seed_extras.append(seed_extra_row_2)
- seed_resize_from_w = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from width", value=0, elem_id=f"{target_interface}_seed_resize_from_w")
- seed_resize_from_h = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from height", value=0, elem_id=f"{target_interface}_seed_resize_from_h")
-
- random_seed.click(fn=None, _js="function(){setRandomSeed('" + target_interface + "_seed')}", show_progress=False, inputs=[], outputs=[])
- random_subseed.click(fn=None, _js="function(){setRandomSeed('" + target_interface + "_subseed')}", show_progress=False, inputs=[], outputs=[])
-
- def change_visibility(show):
- return {comp: gr_show(show) for comp in seed_extras}
-
- seed_checkbox.change(change_visibility, show_progress=False, inputs=[seed_checkbox], outputs=seed_extras)
-
- return seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox
-
-
-
def connect_clear_prompt(button):
"""Given clear button, prompt, and token_counter objects, setup clear prompt button click event"""
button.click(
@@ -191,44 +151,15 @@ def connect_clear_prompt(button): )
-def connect_reuse_seed(seed: gr.Number, reuse_seed: gr.Button, generation_info: gr.Textbox, dummy_component, is_subseed):
- """ Connects a 'reuse (sub)seed' button's click event so that it copies last used
- (sub)seed value from generation info the to the seed field. If copying subseed and subseed strength
- was 0, i.e. no variation seed was used, it copies the normal seed value instead."""
- def copy_seed(gen_info_string: str, index):
- res = -1
-
- try:
- gen_info = json.loads(gen_info_string)
- index -= gen_info.get('index_of_first_image', 0)
-
- if is_subseed and gen_info.get('subseed_strength', 0) > 0:
- all_subseeds = gen_info.get('all_subseeds', [-1])
- res = all_subseeds[index if 0 <= index < len(all_subseeds) else 0]
- else:
- all_seeds = gen_info.get('all_seeds', [-1])
- res = all_seeds[index if 0 <= index < len(all_seeds) else 0]
-
- except json.decoder.JSONDecodeError:
- if gen_info_string:
- errors.report(f"Error parsing JSON generation info: {gen_info_string}")
-
- return [res, gr_show(False)]
-
- reuse_seed.click(
- fn=copy_seed,
- _js="(x, y) => [x, selected_gallery_index()]",
- show_progress=False,
- inputs=[generation_info, dummy_component],
- outputs=[seed, dummy_component]
- )
-
-
-def update_token_counter(text, steps):
+def update_token_counter(text, steps, *, is_positive=True):
try:
text, _ = extra_networks.parse_prompt(text)
- _, prompt_flat_list, _ = prompt_parser.get_multicond_prompt_list([text])
+ if is_positive:
+ _, prompt_flat_list, _ = prompt_parser.get_multicond_prompt_list([text])
+ else:
+ prompt_flat_list = [text]
+
prompt_schedules = prompt_parser.get_learned_conditioning_prompt_schedules(prompt_flat_list, steps)
except Exception:
@@ -242,76 +173,9 @@ def update_token_counter(text, steps): return f"<span class='gr-box gr-text-input'>{token_count}/{max_length}</span>"
-class Toprow:
- """Creates a top row UI with prompts, generate button, styles, extra little buttons for things, and enables some functionality related to their operation"""
+def update_negative_prompt_token_counter(text, steps):
+ return update_token_counter(text, steps, is_positive=False)
- def __init__(self, is_img2img):
- id_part = "img2img" if is_img2img else "txt2img"
- self.id_part = id_part
-
- with gr.Row(elem_id=f"{id_part}_toprow", variant="compact"):
- with gr.Column(elem_id=f"{id_part}_prompt_container", scale=6):
- with gr.Row():
- with gr.Column(scale=80):
- with gr.Row():
- self.prompt = gr.Textbox(label="Prompt", elem_id=f"{id_part}_prompt", show_label=False, lines=3, placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
- self.prompt_img = gr.File(label="", elem_id=f"{id_part}_prompt_image", file_count="single", type="binary", visible=False)
-
- with gr.Row():
- with gr.Column(scale=80):
- with gr.Row():
- self.negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{id_part}_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
-
- self.button_interrogate = None
- self.button_deepbooru = None
- if is_img2img:
- with gr.Column(scale=1, elem_classes="interrogate-col"):
- self.button_interrogate = gr.Button('Interrogate\nCLIP', elem_id="interrogate")
- self.button_deepbooru = gr.Button('Interrogate\nDeepBooru', elem_id="deepbooru")
-
- with gr.Column(scale=1, elem_id=f"{id_part}_actions_column"):
- with gr.Row(elem_id=f"{id_part}_generate_box", elem_classes="generate-box"):
- self.interrupt = gr.Button('Interrupt', elem_id=f"{id_part}_interrupt", elem_classes="generate-box-interrupt")
- self.skip = gr.Button('Skip', elem_id=f"{id_part}_skip", elem_classes="generate-box-skip")
- self.submit = gr.Button('Generate', elem_id=f"{id_part}_generate", variant='primary')
-
- self.skip.click(
- fn=lambda: shared.state.skip(),
- inputs=[],
- outputs=[],
- )
-
- self.interrupt.click(
- fn=lambda: shared.state.interrupt(),
- inputs=[],
- outputs=[],
- )
-
- with gr.Row(elem_id=f"{id_part}_tools"):
- self.paste = ToolButton(value=paste_symbol, elem_id="paste")
- self.clear_prompt_button = ToolButton(value=clear_prompt_symbol, elem_id=f"{id_part}_clear_prompt")
- self.restore_progress_button = ToolButton(value=restore_progress_symbol, elem_id=f"{id_part}_restore_progress", visible=False)
-
- self.token_counter = gr.HTML(value="<span>0/75</span>", elem_id=f"{id_part}_token_counter", elem_classes=["token-counter"])
- self.token_button = gr.Button(visible=False, elem_id=f"{id_part}_token_button")
- self.negative_token_counter = gr.HTML(value="<span>0/75</span>", elem_id=f"{id_part}_negative_token_counter", elem_classes=["token-counter"])
- self.negative_token_button = gr.Button(visible=False, elem_id=f"{id_part}_negative_token_button")
-
- self.clear_prompt_button.click(
- fn=lambda *x: x,
- _js="confirm_clear_prompt",
- inputs=[self.prompt, self.negative_prompt],
- outputs=[self.prompt, self.negative_prompt],
- )
-
- self.ui_styles = ui_prompt_styles.UiPromptStyles(id_part, self.prompt, self.negative_prompt)
-
- self.prompt_img.change(
- fn=modules.images.image_data,
- inputs=[self.prompt_img],
- outputs=[self.prompt, self.prompt_img],
- show_progress=False,
- )
def setup_progressbar(*args, **kwargs):
@@ -351,8 +215,8 @@ def apply_setting(key, value): return getattr(opts, key)
-def create_output_panel(tabname, outdir):
- return ui_common.create_output_panel(tabname, outdir)
+def create_output_panel(tabname, outdir, toprow=None):
+ return ui_common.create_output_panel(tabname, outdir, toprow)
def create_sampler_and_steps_selection(choices, tabname):
@@ -399,18 +263,25 @@ def create_ui(): scripts.scripts_txt2img.initialize_scripts(is_img2img=False)
with gr.Blocks(analytics_enabled=False) as txt2img_interface:
- toprow = Toprow(is_img2img=False)
+ toprow = ui_toprow.Toprow(is_img2img=False, is_compact=shared.opts.compact_prompt_box)
dummy_component = gr.Label(visible=False)
extra_tabs = gr.Tabs(elem_id="txt2img_extra_tabs")
extra_tabs.__enter__()
- with gr.Tab("Generation", id="txt2img_generation") as txt2img_generation_tab, gr.Row(equal_height=False):
- with gr.Column(variant='compact', elem_id="txt2img_settings"):
+ with gr.Tab("Generation", id="txt2img_generation") as txt2img_generation_tab, ResizeHandleRow(equal_height=False):
+ with ExitStack() as stack:
+ if shared.opts.txt2img_settings_accordion:
+ stack.enter_context(gr.Accordion("Open for Settings", open=False))
+ stack.enter_context(gr.Column(variant='compact', elem_id="txt2img_settings"))
+
scripts.scripts_txt2img.prepare_ui()
for category in ordered_ui_categories():
+ if category == "prompt":
+ toprow.create_inline_toprow_prompts()
+
if category == "sampler":
steps, sampler_name = create_sampler_and_steps_selection(sd_samplers.visible_sampler_names(), "txt2img")
@@ -421,7 +292,7 @@ def create_ui(): height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height")
with gr.Column(elem_id="txt2img_dimensions_row", scale=1, elem_classes="dimensions-tools"):
- res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="txt2img_res_switch_btn", label="Switch dims")
+ res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="txt2img_res_switch_btn", tooltip="Switch width/height")
if opts.dimensions_and_batch_together:
with gr.Column(elem_id="txt2img_column_batch"):
@@ -429,44 +300,45 @@ def create_ui(): batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
elif category == "cfg":
- cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="txt2img_cfg_scale")
-
- elif category == "seed":
- seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('txt2img')
+ with gr.Row():
+ cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="txt2img_cfg_scale")
elif category == "checkboxes":
with FormRow(elem_classes="checkboxes-row", variant="compact"):
pass
- elif category == "hires_fix":
- with InputAccordion(False, label="Hires. fix") as enable_hr:
- with enable_hr.extra():
- hr_final_resolution = FormHTML(value="", elem_id="txtimg_hr_finalres", label="Upscaled resolution", interactive=False, min_width=0)
+ elif category == "accordions":
+ with gr.Row(elem_id="txt2img_accordions", elem_classes="accordions"):
+ with InputAccordion(False, label="Hires. fix", elem_id="txt2img_hr") as enable_hr:
+ with enable_hr.extra():
+ hr_final_resolution = FormHTML(value="", elem_id="txtimg_hr_finalres", label="Upscaled resolution", interactive=False, min_width=0)
+
+ with FormRow(elem_id="txt2img_hires_fix_row1", variant="compact"):
+ hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
+ hr_second_pass_steps = gr.Slider(minimum=0, maximum=150, step=1, label='Hires steps', value=0, elem_id="txt2img_hires_steps")
+ denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
- with FormRow(elem_id="txt2img_hires_fix_row1", variant="compact"):
- hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
- hr_second_pass_steps = gr.Slider(minimum=0, maximum=150, step=1, label='Hires steps', value=0, elem_id="txt2img_hires_steps")
- denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
+ with FormRow(elem_id="txt2img_hires_fix_row2", variant="compact"):
+ hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
+ hr_resize_x = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize width to", value=0, elem_id="txt2img_hr_resize_x")
+ hr_resize_y = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize height to", value=0, elem_id="txt2img_hr_resize_y")
- with FormRow(elem_id="txt2img_hires_fix_row2", variant="compact"):
- hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
- hr_resize_x = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize width to", value=0, elem_id="txt2img_hr_resize_x")
- hr_resize_y = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize height to", value=0, elem_id="txt2img_hr_resize_y")
+ with FormRow(elem_id="txt2img_hires_fix_row3", variant="compact", visible=opts.hires_fix_show_sampler) as hr_sampler_container:
- with FormRow(elem_id="txt2img_hires_fix_row3", variant="compact", visible=opts.hires_fix_show_sampler) as hr_sampler_container:
+ hr_checkpoint_name = gr.Dropdown(label='Hires checkpoint', elem_id="hr_checkpoint", choices=["Use same checkpoint"] + modules.sd_models.checkpoint_tiles(use_short=True), value="Use same checkpoint")
+ create_refresh_button(hr_checkpoint_name, modules.sd_models.list_models, lambda: {"choices": ["Use same checkpoint"] + modules.sd_models.checkpoint_tiles(use_short=True)}, "hr_checkpoint_refresh")
- hr_checkpoint_name = gr.Dropdown(label='Hires checkpoint', elem_id="hr_checkpoint", choices=["Use same checkpoint"] + modules.sd_models.checkpoint_tiles(use_short=True), value="Use same checkpoint")
- create_refresh_button(hr_checkpoint_name, modules.sd_models.list_models, lambda: {"choices": ["Use same checkpoint"] + modules.sd_models.checkpoint_tiles(use_short=True)}, "hr_checkpoint_refresh")
+ hr_sampler_name = gr.Dropdown(label='Hires sampling method', elem_id="hr_sampler", choices=["Use same sampler"] + sd_samplers.visible_sampler_names(), value="Use same sampler")
- hr_sampler_name = gr.Dropdown(label='Hires sampling method', elem_id="hr_sampler", choices=["Use same sampler"] + sd_samplers.visible_sampler_names(), value="Use same sampler")
+ with FormRow(elem_id="txt2img_hires_fix_row4", variant="compact", visible=opts.hires_fix_show_prompts) as hr_prompts_container:
+ with gr.Column(scale=80):
+ with gr.Row():
+ hr_prompt = gr.Textbox(label="Hires prompt", elem_id="hires_prompt", show_label=False, lines=3, placeholder="Prompt for hires fix pass.\nLeave empty to use the same prompt as in first pass.", elem_classes=["prompt"])
+ with gr.Column(scale=80):
+ with gr.Row():
+ hr_negative_prompt = gr.Textbox(label="Hires negative prompt", elem_id="hires_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt for hires fix pass.\nLeave empty to use the same negative prompt as in first pass.", elem_classes=["prompt"])
- with FormRow(elem_id="txt2img_hires_fix_row4", variant="compact", visible=opts.hires_fix_show_prompts) as hr_prompts_container:
- with gr.Column(scale=80):
- with gr.Row():
- hr_prompt = gr.Textbox(label="Hires prompt", elem_id="hires_prompt", show_label=False, lines=3, placeholder="Prompt for hires fix pass.\nLeave empty to use the same prompt as in first pass.", elem_classes=["prompt"])
- with gr.Column(scale=80):
- with gr.Row():
- hr_negative_prompt = gr.Textbox(label="Hires negative prompt", elem_id="hires_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt for hires fix pass.\nLeave empty to use the same negative prompt as in first pass.", elem_classes=["prompt"])
+ scripts.scripts_txt2img.setup_ui_for_section(category)
elif category == "batch":
if not opts.dimensions_and_batch_together:
@@ -482,7 +354,7 @@ def create_ui(): with FormGroup(elem_id="txt2img_script_container"):
custom_inputs = scripts.scripts_txt2img.setup_ui()
- else:
+ if category not in {"accordions"}:
scripts.scripts_txt2img.setup_ui_for_section(category)
hr_resolution_preview_inputs = [enable_hr, width, height, hr_scale, hr_resize_x, hr_resize_y]
@@ -504,10 +376,7 @@ def create_ui(): show_progress=False,
)
- txt2img_gallery, generation_info, html_info, html_log = create_output_panel("txt2img", opts.outdir_txt2img_samples)
-
- connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
- connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True)
+ txt2img_gallery, generation_info, html_info, html_log = create_output_panel("txt2img", opts.outdir_txt2img_samples, toprow)
txt2img_args = dict(
fn=wrap_gradio_gpu_call(modules.txt2img.txt2img, extra_outputs=[None, '', '']),
@@ -522,8 +391,6 @@ def create_ui(): batch_count,
batch_size,
cfg_scale,
- seed,
- subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox,
height,
width,
enable_hr,
@@ -574,15 +441,9 @@ def create_ui(): (steps, "Steps"),
(sampler_name, "Sampler"),
(cfg_scale, "CFG scale"),
- (seed, "Seed"),
(width, "Size-1"),
(height, "Size-2"),
(batch_size, "Batch size"),
- (seed_checkbox, lambda d: "Variation seed" in d or "Seed resize from-1" in d),
- (subseed, "Variation seed"),
- (subseed_strength, "Variation seed strength"),
- (seed_resize_from_w, "Seed resize from-1"),
- (seed_resize_from_h, "Seed resize from-2"),
(toprow.ui_styles.dropdown, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update()),
(denoising_strength, "Denoising strength"),
(enable_hr, lambda d: "Denoising strength" in d and ("Hires upscale" in d or "Hires upscaler" in d or "Hires resize-1" in d)),
@@ -610,13 +471,13 @@ def create_ui(): steps,
sampler_name,
cfg_scale,
- seed,
+ scripts.scripts_txt2img.script('Seed').seed,
width,
height,
]
toprow.token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[toprow.prompt, steps], outputs=[toprow.token_counter])
- toprow.negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[toprow.negative_prompt, steps], outputs=[toprow.negative_token_counter])
+ toprow.negative_token_button.click(fn=wrap_queued_call(update_negative_prompt_token_counter), inputs=[toprow.negative_prompt, steps], outputs=[toprow.negative_token_counter])
extra_networks_ui = ui_extra_networks.create_ui(txt2img_interface, [txt2img_generation_tab], 'txt2img')
ui_extra_networks.setup_ui(extra_networks_ui, txt2img_gallery)
@@ -627,13 +488,17 @@ def create_ui(): scripts.scripts_img2img.initialize_scripts(is_img2img=True)
with gr.Blocks(analytics_enabled=False) as img2img_interface:
- toprow = Toprow(is_img2img=True)
+ toprow = ui_toprow.Toprow(is_img2img=True, is_compact=shared.opts.compact_prompt_box)
extra_tabs = gr.Tabs(elem_id="img2img_extra_tabs")
extra_tabs.__enter__()
- with gr.Tab("Generation", id="img2img_generation") as img2img_generation_tab, FormRow(equal_height=False):
- with gr.Column(variant='compact', elem_id="img2img_settings"):
+ with gr.Tab("Generation", id="img2img_generation") as img2img_generation_tab, ResizeHandleRow(equal_height=False):
+ with ExitStack() as stack:
+ if shared.opts.img2img_settings_accordion:
+ stack.enter_context(gr.Accordion("Open for Settings", open=False))
+ stack.enter_context(gr.Column(variant='compact', elem_id="img2img_settings"))
+
copy_image_buttons = []
copy_image_destinations = {}
@@ -650,85 +515,89 @@ def create_ui(): button = gr.Button(title)
copy_image_buttons.append((button, name, elem))
- with gr.Tabs(elem_id="mode_img2img"):
- img2img_selected_tab = gr.State(0)
-
- with gr.TabItem('img2img', id='img2img', elem_id="img2img_img2img_tab") as tab_img2img:
- init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool="editor", image_mode="RGBA", height=opts.img2img_editor_height)
- add_copy_image_controls('img2img', init_img)
-
- with gr.TabItem('Sketch', id='img2img_sketch', elem_id="img2img_img2img_sketch_tab") as tab_sketch:
- sketch = gr.Image(label="Image for img2img", elem_id="img2img_sketch", show_label=False, source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGBA", height=opts.img2img_editor_height, brush_color=opts.img2img_sketch_default_brush_color)
- add_copy_image_controls('sketch', sketch)
-
- with gr.TabItem('Inpaint', id='inpaint', elem_id="img2img_inpaint_tab") as tab_inpaint:
- init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", image_mode="RGBA", height=opts.img2img_editor_height, brush_color=opts.img2img_inpaint_mask_brush_color)
- add_copy_image_controls('inpaint', init_img_with_mask)
-
- with gr.TabItem('Inpaint sketch', id='inpaint_sketch', elem_id="img2img_inpaint_sketch_tab") as tab_inpaint_color:
- inpaint_color_sketch = gr.Image(label="Color sketch inpainting", show_label=False, elem_id="inpaint_sketch", source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGBA", height=opts.img2img_editor_height, brush_color=opts.img2img_inpaint_sketch_default_brush_color)
- inpaint_color_sketch_orig = gr.State(None)
- add_copy_image_controls('inpaint_sketch', inpaint_color_sketch)
-
- def update_orig(image, state):
- if image is not None:
- same_size = state is not None and state.size == image.size
- has_exact_match = np.any(np.all(np.array(image) == np.array(state), axis=-1))
- edited = same_size and has_exact_match
- return image if not edited or state is None else state
-
- inpaint_color_sketch.change(update_orig, [inpaint_color_sketch, inpaint_color_sketch_orig], inpaint_color_sketch_orig)
-
- with gr.TabItem('Inpaint upload', id='inpaint_upload', elem_id="img2img_inpaint_upload_tab") as tab_inpaint_upload:
- init_img_inpaint = gr.Image(label="Image for img2img", show_label=False, source="upload", interactive=True, type="pil", elem_id="img_inpaint_base")
- init_mask_inpaint = gr.Image(label="Mask", source="upload", interactive=True, type="pil", elem_id="img_inpaint_mask")
-
- with gr.TabItem('Batch', id='batch', elem_id="img2img_batch_tab") as tab_batch:
- hidden = '<br>Disabled when launched with --hide-ui-dir-config.' if shared.cmd_opts.hide_ui_dir_config else ''
- gr.HTML(
- "<p style='padding-bottom: 1em;' class=\"text-gray-500\">Process images in a directory on the same machine where the server is running." +
- "<br>Use an empty output directory to save pictures normally instead of writing to the output directory." +
- f"<br>Add inpaint batch mask directory to enable inpaint batch processing."
- f"{hidden}</p>"
- )
- img2img_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, elem_id="img2img_batch_input_dir")
- img2img_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, elem_id="img2img_batch_output_dir")
- img2img_batch_inpaint_mask_dir = gr.Textbox(label="Inpaint batch mask directory (required for inpaint batch processing only)", **shared.hide_dirs, elem_id="img2img_batch_inpaint_mask_dir")
- with gr.Accordion("PNG info", open=False):
- img2img_batch_use_png_info = gr.Checkbox(label="Append png info to prompts", **shared.hide_dirs, elem_id="img2img_batch_use_png_info")
- img2img_batch_png_info_dir = gr.Textbox(label="PNG info directory", **shared.hide_dirs, placeholder="Leave empty to use input directory", elem_id="img2img_batch_png_info_dir")
- img2img_batch_png_info_props = gr.CheckboxGroup(["Prompt", "Negative prompt", "Seed", "CFG scale", "Sampler", "Steps"], label="Parameters to take from png info", info="Prompts from png info will be appended to prompts set in ui.")
-
- img2img_tabs = [tab_img2img, tab_sketch, tab_inpaint, tab_inpaint_color, tab_inpaint_upload, tab_batch]
-
- for i, tab in enumerate(img2img_tabs):
- tab.select(fn=lambda tabnum=i: tabnum, inputs=[], outputs=[img2img_selected_tab])
-
- def copy_image(img):
- if isinstance(img, dict) and 'image' in img:
- return img['image']
-
- return img
-
- for button, name, elem in copy_image_buttons:
- button.click(
- fn=copy_image,
- inputs=[elem],
- outputs=[copy_image_destinations[name]],
- )
- button.click(
- fn=lambda: None,
- _js=f"switch_to_{name.replace(' ', '_')}",
- inputs=[],
- outputs=[],
- )
-
- with FormRow():
- resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
-
scripts.scripts_img2img.prepare_ui()
for category in ordered_ui_categories():
+ if category == "prompt":
+ toprow.create_inline_toprow_prompts()
+
+ if category == "image":
+ with gr.Tabs(elem_id="mode_img2img"):
+ img2img_selected_tab = gr.State(0)
+
+ with gr.TabItem('img2img', id='img2img', elem_id="img2img_img2img_tab") as tab_img2img:
+ init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool="editor", image_mode="RGBA", height=opts.img2img_editor_height)
+ add_copy_image_controls('img2img', init_img)
+
+ with gr.TabItem('Sketch', id='img2img_sketch', elem_id="img2img_img2img_sketch_tab") as tab_sketch:
+ sketch = gr.Image(label="Image for img2img", elem_id="img2img_sketch", show_label=False, source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGB", height=opts.img2img_editor_height, brush_color=opts.img2img_sketch_default_brush_color)
+ add_copy_image_controls('sketch', sketch)
+
+ with gr.TabItem('Inpaint', id='inpaint', elem_id="img2img_inpaint_tab") as tab_inpaint:
+ init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", image_mode="RGBA", height=opts.img2img_editor_height, brush_color=opts.img2img_inpaint_mask_brush_color)
+ add_copy_image_controls('inpaint', init_img_with_mask)
+
+ with gr.TabItem('Inpaint sketch', id='inpaint_sketch', elem_id="img2img_inpaint_sketch_tab") as tab_inpaint_color:
+ inpaint_color_sketch = gr.Image(label="Color sketch inpainting", show_label=False, elem_id="inpaint_sketch", source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGB", height=opts.img2img_editor_height, brush_color=opts.img2img_inpaint_sketch_default_brush_color)
+ inpaint_color_sketch_orig = gr.State(None)
+ add_copy_image_controls('inpaint_sketch', inpaint_color_sketch)
+
+ def update_orig(image, state):
+ if image is not None:
+ same_size = state is not None and state.size == image.size
+ has_exact_match = np.any(np.all(np.array(image) == np.array(state), axis=-1))
+ edited = same_size and has_exact_match
+ return image if not edited or state is None else state
+
+ inpaint_color_sketch.change(update_orig, [inpaint_color_sketch, inpaint_color_sketch_orig], inpaint_color_sketch_orig)
+
+ with gr.TabItem('Inpaint upload', id='inpaint_upload', elem_id="img2img_inpaint_upload_tab") as tab_inpaint_upload:
+ init_img_inpaint = gr.Image(label="Image for img2img", show_label=False, source="upload", interactive=True, type="pil", elem_id="img_inpaint_base")
+ init_mask_inpaint = gr.Image(label="Mask", source="upload", interactive=True, type="pil", image_mode="RGBA", elem_id="img_inpaint_mask")
+
+ with gr.TabItem('Batch', id='batch', elem_id="img2img_batch_tab") as tab_batch:
+ hidden = '<br>Disabled when launched with --hide-ui-dir-config.' if shared.cmd_opts.hide_ui_dir_config else ''
+ gr.HTML(
+ "<p style='padding-bottom: 1em;' class=\"text-gray-500\">Process images in a directory on the same machine where the server is running." +
+ "<br>Use an empty output directory to save pictures normally instead of writing to the output directory." +
+ f"<br>Add inpaint batch mask directory to enable inpaint batch processing."
+ f"{hidden}</p>"
+ )
+ img2img_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, elem_id="img2img_batch_input_dir")
+ img2img_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, elem_id="img2img_batch_output_dir")
+ img2img_batch_inpaint_mask_dir = gr.Textbox(label="Inpaint batch mask directory (required for inpaint batch processing only)", **shared.hide_dirs, elem_id="img2img_batch_inpaint_mask_dir")
+ with gr.Accordion("PNG info", open=False):
+ img2img_batch_use_png_info = gr.Checkbox(label="Append png info to prompts", **shared.hide_dirs, elem_id="img2img_batch_use_png_info")
+ img2img_batch_png_info_dir = gr.Textbox(label="PNG info directory", **shared.hide_dirs, placeholder="Leave empty to use input directory", elem_id="img2img_batch_png_info_dir")
+ img2img_batch_png_info_props = gr.CheckboxGroup(["Prompt", "Negative prompt", "Seed", "CFG scale", "Sampler", "Steps", "Model hash"], label="Parameters to take from png info", info="Prompts from png info will be appended to prompts set in ui.")
+
+ img2img_tabs = [tab_img2img, tab_sketch, tab_inpaint, tab_inpaint_color, tab_inpaint_upload, tab_batch]
+
+ for i, tab in enumerate(img2img_tabs):
+ tab.select(fn=lambda tabnum=i: tabnum, inputs=[], outputs=[img2img_selected_tab])
+
+ def copy_image(img):
+ if isinstance(img, dict) and 'image' in img:
+ return img['image']
+
+ return img
+
+ for button, name, elem in copy_image_buttons:
+ button.click(
+ fn=copy_image,
+ inputs=[elem],
+ outputs=[copy_image_destinations[name]],
+ )
+ button.click(
+ fn=lambda: None,
+ _js=f"switch_to_{name.replace(' ', '_')}",
+ inputs=[],
+ outputs=[],
+ )
+
+ with FormRow():
+ resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
+
if category == "sampler":
steps, sampler_name = create_sampler_and_steps_selection(sd_samplers.visible_sampler_names(), "img2img")
@@ -744,8 +613,8 @@ def create_ui(): width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")
with gr.Column(elem_id="img2img_dimensions_row", scale=1, elem_classes="dimensions-tools"):
- res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="img2img_res_switch_btn")
- detect_image_size_btn = ToolButton(value=detect_image_size_symbol, elem_id="img2img_detect_image_size_btn")
+ res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="img2img_res_switch_btn", tooltip="Switch width/height")
+ detect_image_size_btn = ToolButton(value=detect_image_size_symbol, elem_id="img2img_detect_image_size_btn", tooltip="Auto detect size from img2img")
with gr.Tab(label="Resize by", elem_id="img2img_tab_resize_by") as tab_scale_by:
scale_by = gr.Slider(minimum=0.05, maximum=4.0, step=0.05, label="Scale", value=1.0, elem_id="img2img_scale")
@@ -766,12 +635,6 @@ def create_ui(): scale_by.release(**on_change_args)
button_update_resize_to.click(**on_change_args)
- # the code below is meant to update the resolution label after the image in the image selection UI has changed.
- # as it is now the event keeps firing continuously for inpaint edits, which ruins the page with constant requests.
- # I assume this must be a gradio bug and for now we'll just do it for non-inpaint inputs.
- for component in [init_img, sketch]:
- component.change(fn=lambda: None, _js="updateImg2imgResizeToTextAfterChangingImage", inputs=[], outputs=[], show_progress=False)
-
tab_scale_to.select(fn=lambda: 0, inputs=[], outputs=[selected_scale_tab])
tab_scale_by.select(fn=lambda: 1, inputs=[], outputs=[selected_scale_tab])
@@ -780,20 +643,22 @@ def create_ui(): batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
- elif category == "cfg":
- with FormGroup():
- with FormRow():
- cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="img2img_cfg_scale")
- image_cfg_scale = gr.Slider(minimum=0, maximum=3.0, step=0.05, label='Image CFG Scale', value=1.5, elem_id="img2img_image_cfg_scale", visible=False)
- denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.75, elem_id="img2img_denoising_strength")
+ elif category == "denoising":
+ denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.75, elem_id="img2img_denoising_strength")
- elif category == "seed":
- seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('img2img')
+ elif category == "cfg":
+ with gr.Row():
+ cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="img2img_cfg_scale")
+ image_cfg_scale = gr.Slider(minimum=0, maximum=3.0, step=0.05, label='Image CFG Scale', value=1.5, elem_id="img2img_image_cfg_scale", visible=False)
elif category == "checkboxes":
with FormRow(elem_classes="checkboxes-row", variant="compact"):
pass
+ elif category == "accordions":
+ with gr.Row(elem_id="img2img_accordions", elem_classes="accordions"):
+ scripts.scripts_img2img.setup_ui_for_section(category)
+
elif category == "batch":
if not opts.dimensions_and_batch_together:
with FormRow(elem_id="img2img_column_batch"):
@@ -827,22 +692,26 @@ def create_ui(): with gr.Column(scale=4):
inpaint_full_res_padding = gr.Slider(label='Only masked padding, pixels', minimum=0, maximum=256, step=4, value=32, elem_id="img2img_inpaint_full_res_padding")
- def select_img2img_tab(tab):
- return gr.update(visible=tab in [2, 3, 4]), gr.update(visible=tab == 3),
-
- for i, elem in enumerate(img2img_tabs):
- elem.select(
- fn=lambda tab=i: select_img2img_tab(tab),
- inputs=[],
- outputs=[inpaint_controls, mask_alpha],
- )
- else:
+ if category not in {"accordions"}:
scripts.scripts_img2img.setup_ui_for_section(category)
- img2img_gallery, generation_info, html_info, html_log = create_output_panel("img2img", opts.outdir_img2img_samples)
+ # the code below is meant to update the resolution label after the image in the image selection UI has changed.
+ # as it is now the event keeps firing continuously for inpaint edits, which ruins the page with constant requests.
+ # I assume this must be a gradio bug and for now we'll just do it for non-inpaint inputs.
+ for component in [init_img, sketch]:
+ component.change(fn=lambda: None, _js="updateImg2imgResizeToTextAfterChangingImage", inputs=[], outputs=[], show_progress=False)
- connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
- connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True)
+ def select_img2img_tab(tab):
+ return gr.update(visible=tab in [2, 3, 4]), gr.update(visible=tab == 3),
+
+ for i, elem in enumerate(img2img_tabs):
+ elem.select(
+ fn=lambda tab=i: select_img2img_tab(tab),
+ inputs=[],
+ outputs=[inpaint_controls, mask_alpha],
+ )
+
+ img2img_gallery, generation_info, html_info, html_log = create_output_panel("img2img", opts.outdir_img2img_samples, toprow)
img2img_args = dict(
fn=wrap_gradio_gpu_call(modules.img2img.img2img, extra_outputs=[None, '', '']),
@@ -870,8 +739,6 @@ def create_ui(): cfg_scale,
image_cfg_scale,
denoising_strength,
- seed,
- subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox,
selected_scale_tab,
height,
width,
@@ -958,15 +825,9 @@ def create_ui(): (sampler_name, "Sampler"),
(cfg_scale, "CFG scale"),
(image_cfg_scale, "Image CFG scale"),
- (seed, "Seed"),
(width, "Size-1"),
(height, "Size-2"),
(batch_size, "Batch size"),
- (seed_checkbox, lambda d: "Variation seed" in d or "Seed resize from-1" in d),
- (subseed, "Variation seed"),
- (subseed_strength, "Variation seed strength"),
- (seed_resize_from_w, "Seed resize from-1"),
- (seed_resize_from_h, "Seed resize from-2"),
(toprow.ui_styles.dropdown, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update()),
(denoising_strength, "Denoising strength"),
(mask_blur, "Mask blur"),
@@ -1370,17 +1231,14 @@ def create_ui(): with gr.TabItem(label, id=ifid, elem_id=f"tab_{ifid}"):
interface.render()
- for interface, _label, ifid in interfaces:
- if ifid in ["extensions", "settings"]:
- continue
-
- loadsave.add_block(interface, ifid)
+ if ifid not in ["extensions", "settings"]:
+ loadsave.add_block(interface, ifid)
loadsave.add_component(f"webui/Tabs@{tabs.elem_id}", tabs)
loadsave.setup_ui()
- if os.path.exists(os.path.join(script_path, "notification.mp3")):
+ if os.path.exists(os.path.join(script_path, "notification.mp3")) and shared.opts.notification_audio:
gr.Audio(interactive=False, value=os.path.join(script_path, "notification.mp3"), elem_id="audio_notification", visible=False)
footer = shared.html("footer.html")
@@ -1432,7 +1290,6 @@ checkpoint: <a id="sd_checkpoint_hash">N/A</a> def setup_ui_api(app):
from pydantic import BaseModel, Field
- from typing import List
class QuicksettingsHint(BaseModel):
name: str = Field(title="Name of the quicksettings field")
@@ -1441,7 +1298,7 @@ def setup_ui_api(app): def quicksettings_hint():
return [QuicksettingsHint(name=k, label=v.label) for k, v in opts.data_labels.items()]
- app.add_api_route("/internal/quicksettings-hint", quicksettings_hint, methods=["GET"], response_model=List[QuicksettingsHint])
+ app.add_api_route("/internal/quicksettings-hint", quicksettings_hint, methods=["GET"], response_model=list[QuicksettingsHint])
app.add_api_route("/internal/ping", lambda: {}, methods=["GET"])
@@ -1451,7 +1308,7 @@ def setup_ui_api(app): from fastapi.responses import PlainTextResponse
text = sysinfo.get()
- filename = f"sysinfo-{datetime.datetime.utcnow().strftime('%Y-%m-%d-%H-%M')}.txt"
+ filename = f"sysinfo-{datetime.datetime.utcnow().strftime('%Y-%m-%d-%H-%M')}.json"
return PlainTextResponse(text, headers={'Content-Disposition': f'{"attachment" if attachment else "inline"}; filename="{filename}"'})
diff --git a/modules/ui_common.py b/modules/ui_common.py index 99d19ff0..032ec4af 100644 --- a/modules/ui_common.py +++ b/modules/ui_common.py @@ -104,7 +104,7 @@ def save_files(js_data, images, do_make_zip, index): return gr.File.update(value=fullfns, visible=True), plaintext_to_html(f"Saved: {filenames[0]}")
-def create_output_panel(tabname, outdir):
+def create_output_panel(tabname, outdir, toprow=None):
def open_folder(f):
if not os.path.exists(f):
@@ -130,20 +130,27 @@ Requested path was: {f} else:
sp.Popen(["xdg-open", path])
- with gr.Column(variant='panel', elem_id=f"{tabname}_results"):
- with gr.Group(elem_id=f"{tabname}_gallery_container"):
- result_gallery = gr.Gallery(label='Output', show_label=False, elem_id=f"{tabname}_gallery", columns=4)
+ with gr.Column(elem_id=f"{tabname}_results"):
+ if toprow:
+ toprow.create_inline_toprow_image()
- generation_info = None
- with gr.Column():
+ with gr.Column(variant='panel', elem_id=f"{tabname}_results_panel"):
+ with gr.Group(elem_id=f"{tabname}_gallery_container"):
+ result_gallery = gr.Gallery(label='Output', show_label=False, elem_id=f"{tabname}_gallery", columns=4, preview=True, height=shared.opts.gallery_height or None)
+
+ generation_info = None
with gr.Row(elem_id=f"image_buttons_{tabname}", elem_classes="image-buttons"):
- open_folder_button = gr.Button(folder_symbol, visible=not shared.cmd_opts.hide_ui_dir_config)
+ open_folder_button = ToolButton(folder_symbol, elem_id=f'{tabname}_open_folder', visible=not shared.cmd_opts.hide_ui_dir_config, tooltip="Open images output directory.")
if tabname != "extras":
- save = gr.Button('Save', elem_id=f'save_{tabname}')
- save_zip = gr.Button('Zip', elem_id=f'save_zip_{tabname}')
+ save = ToolButton('💾', elem_id=f'save_{tabname}', tooltip=f"Save the image to a dedicated directory ({shared.opts.outdir_save}).")
+ save_zip = ToolButton('🗃️', elem_id=f'save_zip_{tabname}', tooltip=f"Save zip archive with images to a dedicated directory ({shared.opts.outdir_save})")
- buttons = parameters_copypaste.create_buttons(["img2img", "inpaint", "extras"])
+ buttons = {
+ 'img2img': ToolButton('🖼️', elem_id=f'{tabname}_send_to_img2img', tooltip="Send image and generation parameters to img2img tab."),
+ 'inpaint': ToolButton('🎨️', elem_id=f'{tabname}_send_to_inpaint', tooltip="Send image and generation parameters to img2img inpaint tab."),
+ 'extras': ToolButton('📐', elem_id=f'{tabname}_send_to_extras', tooltip="Send image and generation parameters to extras tab.")
+ }
open_folder_button.click(
fn=lambda: open_folder(shared.opts.outdir_samples or outdir),
@@ -257,7 +264,7 @@ def setup_dialog(button_show, dialog, *, button_close=None): fn=lambda: gr.update(visible=True),
inputs=[],
outputs=[dialog],
- ).then(fn=None, _js="function(){ popup(gradioApp().getElementById('" + dialog.elem_id + "')); }")
+ ).then(fn=None, _js="function(){ popupId('" + dialog.elem_id + "'); }")
if button_close:
button_close.click(fn=None, _js="closePopup")
diff --git a/modules/ui_components.py b/modules/ui_components.py index bfe2fbd9..55979f62 100644 --- a/modules/ui_components.py +++ b/modules/ui_components.py @@ -20,6 +20,18 @@ class ToolButton(FormComponent, gr.Button): return "button"
+class ResizeHandleRow(gr.Row):
+ """Same as gr.Row but fits inside gradio forms"""
+
+ def __init__(self, **kwargs):
+ super().__init__(**kwargs)
+
+ self.elem_classes.append("resize-handle-row")
+
+ def get_block_name(self):
+ return "row"
+
+
class FormRow(FormComponent, gr.Row):
"""Same as gr.Row but fits inside gradio forms"""
@@ -87,13 +99,23 @@ class InputAccordion(gr.Checkbox): self.accordion_id = f"input-accordion-{InputAccordion.global_index}"
InputAccordion.global_index += 1
- kwargs['elem_id'] = self.accordion_id + "-checkbox"
- kwargs['visible'] = False
- super().__init__(value, **kwargs)
+ kwargs_checkbox = {
+ **kwargs,
+ "elem_id": f"{self.accordion_id}-checkbox",
+ "visible": False,
+ }
+ super().__init__(value, **kwargs_checkbox)
self.change(fn=None, _js='function(checked){ inputAccordionChecked("' + self.accordion_id + '", checked); }', inputs=[self])
- self.accordion = gr.Accordion(kwargs.get('label', 'Accordion'), open=value, elem_id=self.accordion_id, elem_classes=['input-accordion'])
+ kwargs_accordion = {
+ **kwargs,
+ "elem_id": self.accordion_id,
+ "label": kwargs.get('label', 'Accordion'),
+ "elem_classes": ['input-accordion'],
+ "open": value,
+ }
+ self.accordion = gr.Accordion(**kwargs_accordion)
def extra(self):
"""Allows you to put something into the label of the accordion.
diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py index 15a8b0bf..c0a73b57 100644 --- a/modules/ui_extensions.py +++ b/modules/ui_extensions.py @@ -2,7 +2,7 @@ import json import os
import threading
import time
-from datetime import datetime
+from datetime import datetime, timezone
import git
@@ -65,7 +65,7 @@ def save_config_state(name): filename = os.path.join(config_states_dir, f"{timestamp}_{name}.json")
print(f"Saving backup of webui/extension state to {filename}.")
with open(filename, "w", encoding="utf-8") as f:
- json.dump(current_config_state, f)
+ json.dump(current_config_state, f, indent=4)
config_states.list_config_states()
new_value = next(iter(config_states.all_config_states.keys()), "Current")
new_choices = ["Current"] + list(config_states.all_config_states.keys())
@@ -177,7 +177,7 @@ def extension_table(): <td>{remote}</td>
<td>{ext.branch}</td>
<td>{version_link}</td>
- <td>{time.asctime(time.gmtime(ext.commit_date))}</td>
+ <td>{datetime.fromtimestamp(ext.commit_date) if ext.commit_date else ""}</td>
<td{' class="extension_status"' if ext.remote is not None else ''}>{ext_status}</td>
</tr>
"""
@@ -197,122 +197,132 @@ def update_config_states_table(state_name): config_state = config_states.all_config_states[state_name]
config_name = config_state.get("name", "Config")
- created_date = time.asctime(time.gmtime(config_state["created_at"]))
+ created_date = datetime.fromtimestamp(config_state["created_at"]).strftime('%Y-%m-%d %H:%M:%S')
filepath = config_state.get("filepath", "<unknown>")
- code = f"""<!-- {time.time()} -->"""
-
- webui_remote = config_state["webui"]["remote"] or ""
- webui_branch = config_state["webui"]["branch"]
- webui_commit_hash = config_state["webui"]["commit_hash"] or "<unknown>"
- webui_commit_date = config_state["webui"]["commit_date"]
- if webui_commit_date:
- webui_commit_date = time.asctime(time.gmtime(webui_commit_date))
- else:
- webui_commit_date = "<unknown>"
-
- remote = f"""<a href="{html.escape(webui_remote)}" target="_blank">{html.escape(webui_remote or '')}</a>"""
- commit_link = make_commit_link(webui_commit_hash, webui_remote)
- date_link = make_commit_link(webui_commit_hash, webui_remote, webui_commit_date)
-
- current_webui = config_states.get_webui_config()
-
- style_remote = ""
- style_branch = ""
- style_commit = ""
- if current_webui["remote"] != webui_remote:
- style_remote = STYLE_PRIMARY
- if current_webui["branch"] != webui_branch:
- style_branch = STYLE_PRIMARY
- if current_webui["commit_hash"] != webui_commit_hash:
- style_commit = STYLE_PRIMARY
-
- code += f"""<h2>Config Backup: {config_name}</h2>
- <div><b>Filepath:</b> {filepath}</div>
- <div><b>Created at:</b> {created_date}</div>"""
-
- code += f"""<h2>WebUI State</h2>
- <table id="config_state_webui">
- <thead>
- <tr>
- <th>URL</th>
- <th>Branch</th>
- <th>Commit</th>
- <th>Date</th>
- </tr>
- </thead>
- <tbody>
- <tr>
- <td><label{style_remote}>{remote}</label></td>
- <td><label{style_branch}>{webui_branch}</label></td>
- <td><label{style_commit}>{commit_link}</label></td>
- <td><label{style_commit}>{date_link}</label></td>
- </tr>
- </tbody>
- </table>
- """
-
- code += """<h2>Extension State</h2>
- <table id="config_state_extensions">
- <thead>
- <tr>
- <th>Extension</th>
- <th>URL</th>
- <th>Branch</th>
- <th>Commit</th>
- <th>Date</th>
- </tr>
- </thead>
- <tbody>
- """
-
- ext_map = {ext.name: ext for ext in extensions.extensions}
-
- for ext_name, ext_conf in config_state["extensions"].items():
- ext_remote = ext_conf["remote"] or ""
- ext_branch = ext_conf["branch"] or "<unknown>"
- ext_enabled = ext_conf["enabled"]
- ext_commit_hash = ext_conf["commit_hash"] or "<unknown>"
- ext_commit_date = ext_conf["commit_date"]
- if ext_commit_date:
- ext_commit_date = time.asctime(time.gmtime(ext_commit_date))
+ try:
+ webui_remote = config_state["webui"]["remote"] or ""
+ webui_branch = config_state["webui"]["branch"]
+ webui_commit_hash = config_state["webui"]["commit_hash"] or "<unknown>"
+ webui_commit_date = config_state["webui"]["commit_date"]
+ if webui_commit_date:
+ webui_commit_date = time.asctime(time.gmtime(webui_commit_date))
else:
- ext_commit_date = "<unknown>"
+ webui_commit_date = "<unknown>"
- remote = f"""<a href="{html.escape(ext_remote)}" target="_blank">{html.escape(ext_remote or '')}</a>"""
- commit_link = make_commit_link(ext_commit_hash, ext_remote)
- date_link = make_commit_link(ext_commit_hash, ext_remote, ext_commit_date)
+ remote = f"""<a href="{html.escape(webui_remote)}" target="_blank">{html.escape(webui_remote or '')}</a>"""
+ commit_link = make_commit_link(webui_commit_hash, webui_remote)
+ date_link = make_commit_link(webui_commit_hash, webui_remote, webui_commit_date)
+
+ current_webui = config_states.get_webui_config()
- style_enabled = ""
style_remote = ""
style_branch = ""
style_commit = ""
- if ext_name in ext_map:
- current_ext = ext_map[ext_name]
- current_ext.read_info_from_repo()
- if current_ext.enabled != ext_enabled:
- style_enabled = STYLE_PRIMARY
- if current_ext.remote != ext_remote:
- style_remote = STYLE_PRIMARY
- if current_ext.branch != ext_branch:
- style_branch = STYLE_PRIMARY
- if current_ext.commit_hash != ext_commit_hash:
- style_commit = STYLE_PRIMARY
-
- code += f"""
- <tr>
- <td><label{style_enabled}><input class="gr-check-radio gr-checkbox" type="checkbox" disabled="true" {'checked="checked"' if ext_enabled else ''}>{html.escape(ext_name)}</label></td>
- <td><label{style_remote}>{remote}</label></td>
- <td><label{style_branch}>{ext_branch}</label></td>
- <td><label{style_commit}>{commit_link}</label></td>
- <td><label{style_commit}>{date_link}</label></td>
- </tr>
- """
-
- code += """
- </tbody>
- </table>
- """
+ if current_webui["remote"] != webui_remote:
+ style_remote = STYLE_PRIMARY
+ if current_webui["branch"] != webui_branch:
+ style_branch = STYLE_PRIMARY
+ if current_webui["commit_hash"] != webui_commit_hash:
+ style_commit = STYLE_PRIMARY
+
+ code = f"""<!-- {time.time()} -->
+<h2>Config Backup: {config_name}</h2>
+<div><b>Filepath:</b> {filepath}</div>
+<div><b>Created at:</b> {created_date}</div>
+<h2>WebUI State</h2>
+<table id="config_state_webui">
+ <thead>
+ <tr>
+ <th>URL</th>
+ <th>Branch</th>
+ <th>Commit</th>
+ <th>Date</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <td>
+ <label{style_remote}>{remote}</label>
+ </td>
+ <td>
+ <label{style_branch}>{webui_branch}</label>
+ </td>
+ <td>
+ <label{style_commit}>{commit_link}</label>
+ </td>
+ <td>
+ <label{style_commit}>{date_link}</label>
+ </td>
+ </tr>
+ </tbody>
+</table>
+<h2>Extension State</h2>
+<table id="config_state_extensions">
+ <thead>
+ <tr>
+ <th>Extension</th>
+ <th>URL</th>
+ <th>Branch</th>
+ <th>Commit</th>
+ <th>Date</th>
+ </tr>
+ </thead>
+ <tbody>
+"""
+
+ ext_map = {ext.name: ext for ext in extensions.extensions}
+
+ for ext_name, ext_conf in config_state["extensions"].items():
+ ext_remote = ext_conf["remote"] or ""
+ ext_branch = ext_conf["branch"] or "<unknown>"
+ ext_enabled = ext_conf["enabled"]
+ ext_commit_hash = ext_conf["commit_hash"] or "<unknown>"
+ ext_commit_date = ext_conf["commit_date"]
+ if ext_commit_date:
+ ext_commit_date = time.asctime(time.gmtime(ext_commit_date))
+ else:
+ ext_commit_date = "<unknown>"
+
+ remote = f"""<a href="{html.escape(ext_remote)}" target="_blank">{html.escape(ext_remote or '')}</a>"""
+ commit_link = make_commit_link(ext_commit_hash, ext_remote)
+ date_link = make_commit_link(ext_commit_hash, ext_remote, ext_commit_date)
+
+ style_enabled = ""
+ style_remote = ""
+ style_branch = ""
+ style_commit = ""
+ if ext_name in ext_map:
+ current_ext = ext_map[ext_name]
+ current_ext.read_info_from_repo()
+ if current_ext.enabled != ext_enabled:
+ style_enabled = STYLE_PRIMARY
+ if current_ext.remote != ext_remote:
+ style_remote = STYLE_PRIMARY
+ if current_ext.branch != ext_branch:
+ style_branch = STYLE_PRIMARY
+ if current_ext.commit_hash != ext_commit_hash:
+ style_commit = STYLE_PRIMARY
+
+ code += f""" <tr>
+ <td><label{style_enabled}><input class="gr-check-radio gr-checkbox" type="checkbox" disabled="true" {'checked="checked"' if ext_enabled else ''}>{html.escape(ext_name)}</label></td>
+ <td><label{style_remote}>{remote}</label></td>
+ <td><label{style_branch}>{ext_branch}</label></td>
+ <td><label{style_commit}>{commit_link}</label></td>
+ <td><label{style_commit}>{date_link}</label></td>
+ </tr>
+"""
+
+ code += """ </tbody>
+</table>"""
+
+ except Exception as e:
+ print(f"[ERROR]: Config states {filepath}, {e}")
+ code = f"""<!-- {time.time()} -->
+<h2>Config Backup: {config_name}</h2>
+<div><b>Filepath:</b> {filepath}</div>
+<div><b>Created at:</b> {created_date}</div>
+<h2>This file is corrupted</h2>"""
return code
@@ -432,7 +442,7 @@ sort_ordering = [ def get_date(info: dict, key):
try:
- return datetime.strptime(info.get(key), "%Y-%m-%dT%H:%M:%SZ").strftime("%Y-%m-%d")
+ return datetime.strptime(info.get(key), "%Y-%m-%dT%H:%M:%SZ").replace(tzinfo=timezone.utc).astimezone().strftime("%Y-%m-%d")
except (ValueError, TypeError):
return ''
@@ -547,8 +557,12 @@ def create_ui(): msg = '"--disable-extra-extensions" was used, remove it to load all extensions again'
html = f'<span style="color: var(--primary-400);">{msg}</span>'
- info = gr.HTML(html)
- extensions_table = gr.HTML('Loading...')
+ with gr.Row():
+ info = gr.HTML(html)
+
+ with gr.Row(elem_classes="progress-container"):
+ extensions_table = gr.HTML('Loading...', elem_id="extensions_installed_html")
+
ui.load(fn=extension_table, inputs=[], outputs=[extensions_table])
apply.click(
diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py index 063bd7b8..f03e2033 100644 --- a/modules/ui_extra_networks.py +++ b/modules/ui_extra_networks.py @@ -1,3 +1,4 @@ +import functools
import os.path
import urllib.parse
from pathlib import Path
@@ -15,6 +16,17 @@ from modules.ui_components import ToolButton extra_pages = []
allowed_dirs = set()
+default_allowed_preview_extensions = ["png", "jpg", "jpeg", "webp", "gif"]
+
+
+@functools.cache
+def allowed_preview_extensions_with_extra(extra_extensions=None):
+ return set(default_allowed_preview_extensions) | set(extra_extensions or [])
+
+
+def allowed_preview_extensions():
+ return allowed_preview_extensions_with_extra((shared.opts.samples_format, ))
+
def register_page(page):
"""registers extra networks page for the UI; recommend doing it in on_before_ui() callback for extensions"""
@@ -33,9 +45,9 @@ def fetch_file(filename: str = ""): if not any(Path(x).absolute() in Path(filename).absolute().parents for x in allowed_dirs):
raise ValueError(f"File cannot be fetched: {filename}. Must be in one of directories registered by extra pages.")
- ext = os.path.splitext(filename)[1].lower()
- if ext not in (".png", ".jpg", ".jpeg", ".webp", ".gif"):
- raise ValueError(f"File cannot be fetched: {filename}. Only png, jpg, webp, and gif.")
+ ext = os.path.splitext(filename)[1].lower()[1:]
+ if ext not in allowed_preview_extensions():
+ raise ValueError(f"File cannot be fetched: {filename}. Extensions allowed: {allowed_preview_extensions()}.")
# would profit from returning 304
return FileResponse(filename, headers={"Accept-Ranges": "bytes"})
@@ -91,6 +103,7 @@ class ExtraNetworksPage: self.name = title.lower()
self.id_page = self.name.replace(" ", "_")
self.card_page = shared.html("extra-networks-card.html")
+ self.allow_prompt = True
self.allow_negative_prompt = False
self.metadata = {}
self.items = {}
@@ -213,9 +226,9 @@ class ExtraNetworksPage: metadata_button = ""
metadata = item.get("metadata")
if metadata:
- metadata_button = f"<div class='metadata-button card-button' title='Show internal metadata' onclick='extraNetworksRequestMetadata(event, {quote_js(self.name)}, {quote_js(item['name'])})'></div>"
+ metadata_button = f"<div class='metadata-button card-button' title='Show internal metadata' onclick='extraNetworksRequestMetadata(event, {quote_js(self.name)}, {quote_js(html.escape(item['name']))})'></div>"
- edit_button = f"<div class='edit-button card-button' title='Edit metadata' onclick='extraNetworksEditUserMetadata(event, {quote_js(tabname)}, {quote_js(self.id_page)}, {quote_js(item['name'])})'></div>"
+ edit_button = f"<div class='edit-button card-button' title='Edit metadata' onclick='extraNetworksEditUserMetadata(event, {quote_js(tabname)}, {quote_js(self.id_page)}, {quote_js(html.escape(item['name']))})'></div>"
local_path = ""
filename = item.get("filename", "")
@@ -235,7 +248,7 @@ class ExtraNetworksPage: if search_only and shared.opts.extra_networks_hidden_models == "Never":
return ""
- sort_keys = " ".join([html.escape(f'data-sort-{k}={v}') for k, v in item.get("sort_keys", {}).items()]).strip()
+ sort_keys = " ".join([f'data-sort-{k}="{html.escape(str(v))}"' for k, v in item.get("sort_keys", {}).items()]).strip()
args = {
"background_image": background_image,
@@ -266,6 +279,7 @@ class ExtraNetworksPage: "date_created": int(stat.st_ctime or 0),
"date_modified": int(stat.st_mtime or 0),
"name": pth.name.lower(),
+ "path": str(pth.parent).lower(),
}
def find_preview(self, path):
@@ -273,11 +287,7 @@ class ExtraNetworksPage: Find a preview PNG for a given path (without extension) and call link_preview on it.
"""
- preview_extensions = ["png", "jpg", "jpeg", "webp"]
- if shared.opts.samples_format not in preview_extensions:
- preview_extensions.append(shared.opts.samples_format)
-
- potential_files = sum([[path + "." + ext, path + ".preview." + ext] for ext in preview_extensions], [])
+ potential_files = sum([[path + "." + ext, path + ".preview." + ext] for ext in allowed_preview_extensions()], [])
for file in potential_files:
if os.path.isfile(file):
@@ -359,7 +369,7 @@ def create_ui(interface: gr.Blocks, unrelated_tabs, tabname): related_tabs = []
for page in ui.stored_extra_pages:
- with gr.Tab(page.title, id=page.id_page) as tab:
+ with gr.Tab(page.title, elem_id=f"{tabname}_{page.id_page}", elem_classes=["extra-page"]) as tab:
elem_id = f"{tabname}_{page.id_page}_cards_html"
page_elem = gr.HTML('Loading...', elem_id=elem_id)
ui.pages.append(page_elem)
@@ -373,19 +383,28 @@ def create_ui(interface: gr.Blocks, unrelated_tabs, tabname): related_tabs.append(tab)
edit_search = gr.Textbox('', show_label=False, elem_id=tabname+"_extra_search", elem_classes="search", placeholder="Search...", visible=False, interactive=True)
- dropdown_sort = gr.Dropdown(choices=['Default Sort', 'Date Created', 'Date Modified', 'Name'], value='Default Sort', elem_id=tabname+"_extra_sort", elem_classes="sort", multiselect=False, visible=False, show_label=False, interactive=True, label=tabname+"_extra_sort_order")
- button_sortorder = ToolButton(switch_values_symbol, elem_id=tabname+"_extra_sortorder", elem_classes="sortorder", visible=False)
+ dropdown_sort = gr.Dropdown(choices=['Path', 'Name', 'Date Created', 'Date Modified', ], value=shared.opts.extra_networks_card_order_field, elem_id=tabname+"_extra_sort", elem_classes="sort", multiselect=False, visible=False, show_label=False, interactive=True, label=tabname+"_extra_sort_order")
+ button_sortorder = ToolButton(switch_values_symbol, elem_id=tabname+"_extra_sortorder", elem_classes=["sortorder"] + ([] if shared.opts.extra_networks_card_order == "Ascending" else ["sortReverse"]), visible=False, tooltip="Invert sort order")
button_refresh = gr.Button('Refresh', elem_id=tabname+"_extra_refresh", visible=False)
checkbox_show_dirs = gr.Checkbox(True, label='Show dirs', elem_id=tabname+"_extra_show_dirs", elem_classes="show-dirs", visible=False)
ui.button_save_preview = gr.Button('Save preview', elem_id=tabname+"_save_preview", visible=False)
ui.preview_target_filename = gr.Textbox('Preview save filename', elem_id=tabname+"_preview_filename", visible=False)
+ tab_controls = [edit_search, dropdown_sort, button_sortorder, button_refresh, checkbox_show_dirs]
+
for tab in unrelated_tabs:
- tab.select(fn=lambda: [gr.update(visible=False) for _ in range(5)], inputs=[], outputs=[edit_search, dropdown_sort, button_sortorder, button_refresh, checkbox_show_dirs], show_progress=False)
+ tab.select(fn=lambda: [gr.update(visible=False) for _ in tab_controls], _js='function(){ extraNetworksUrelatedTabSelected("' + tabname + '"); }', inputs=[], outputs=tab_controls, show_progress=False)
+
+ for page, tab in zip(ui.stored_extra_pages, related_tabs):
+ allow_prompt = "true" if page.allow_prompt else "false"
+ allow_negative_prompt = "true" if page.allow_negative_prompt else "false"
+
+ jscode = 'extraNetworksTabSelected("' + tabname + '", "' + f"{tabname}_{page.id_page}" + '", ' + allow_prompt + ', ' + allow_negative_prompt + ');'
+
+ tab.select(fn=lambda: [gr.update(visible=True) for _ in tab_controls], _js='function(){ ' + jscode + ' }', inputs=[], outputs=tab_controls, show_progress=False)
- for tab in related_tabs:
- tab.select(fn=lambda: [gr.update(visible=True) for _ in range(5)], inputs=[], outputs=[edit_search, dropdown_sort, button_sortorder, button_refresh, checkbox_show_dirs], show_progress=False)
+ dropdown_sort.change(fn=lambda: None, _js="function(){ applyExtraNetworkSort('" + tabname + "'); }")
def pages_html():
if not ui.pages_contents:
diff --git a/modules/ui_extra_networks_checkpoints.py b/modules/ui_extra_networks_checkpoints.py index 77885022..1693e71f 100644 --- a/modules/ui_extra_networks_checkpoints.py +++ b/modules/ui_extra_networks_checkpoints.py @@ -10,15 +10,21 @@ class ExtraNetworksPageCheckpoints(ui_extra_networks.ExtraNetworksPage): def __init__(self):
super().__init__('Checkpoints')
+ self.allow_prompt = False
+
def refresh(self):
shared.refresh_checkpoints()
def create_item(self, name, index=None, enable_filter=True):
checkpoint: sd_models.CheckpointInfo = sd_models.checkpoint_aliases.get(name)
+ if checkpoint is None:
+ return
+
path, ext = os.path.splitext(checkpoint.filename)
return {
"name": checkpoint.name_for_extra,
"filename": checkpoint.filename,
+ "shorthash": checkpoint.shorthash,
"preview": self.find_preview(path),
"description": self.find_description(path),
"search_term": self.search_terms_from_path(checkpoint.filename) + " " + (checkpoint.sha256 or ""),
@@ -29,8 +35,12 @@ class ExtraNetworksPageCheckpoints(ui_extra_networks.ExtraNetworksPage): }
def list_items(self):
- for index, name in enumerate(sd_models.checkpoints_list):
- yield self.create_item(name, index)
+ # instantiate a list to protect against concurrent modification
+ names = list(sd_models.checkpoints_list)
+ for index, name in enumerate(names):
+ item = self.create_item(name, index)
+ if item is not None:
+ yield item
def allowed_directories_for_previews(self):
return [v for v in [shared.cmd_opts.ckpt_dir, sd_models.model_path] if v is not None]
diff --git a/modules/ui_extra_networks_hypernets.py b/modules/ui_extra_networks_hypernets.py index 514a4562..c96c4fa3 100644 --- a/modules/ui_extra_networks_hypernets.py +++ b/modules/ui_extra_networks_hypernets.py @@ -2,6 +2,7 @@ import os from modules import shared, ui_extra_networks
from modules.ui_extra_networks import quote_js
+from modules.hashes import sha256_from_cache
class ExtraNetworksPageHypernetworks(ui_extra_networks.ExtraNetworksPage):
@@ -12,23 +13,33 @@ class ExtraNetworksPageHypernetworks(ui_extra_networks.ExtraNetworksPage): shared.reload_hypernetworks()
def create_item(self, name, index=None, enable_filter=True):
- full_path = shared.hypernetworks[name]
+ full_path = shared.hypernetworks.get(name)
+ if full_path is None:
+ return
+
path, ext = os.path.splitext(full_path)
+ sha256 = sha256_from_cache(full_path, f'hypernet/{name}')
+ shorthash = sha256[0:10] if sha256 else None
return {
"name": name,
"filename": full_path,
+ "shorthash": shorthash,
"preview": self.find_preview(path),
"description": self.find_description(path),
- "search_term": self.search_terms_from_path(path),
+ "search_term": self.search_terms_from_path(path) + " " + (sha256 or ""),
"prompt": quote_js(f"<hypernet:{name}:") + " + opts.extra_networks_default_multiplier + " + quote_js(">"),
"local_preview": f"{path}.preview.{shared.opts.samples_format}",
"sort_keys": {'default': index, **self.get_sort_keys(path + ext)},
}
def list_items(self):
- for index, name in enumerate(shared.hypernetworks):
- yield self.create_item(name, index)
+ # instantiate a list to protect against concurrent modification
+ names = list(shared.hypernetworks)
+ for index, name in enumerate(names):
+ item = self.create_item(name, index)
+ if item is not None:
+ yield item
def allowed_directories_for_previews(self):
return [shared.cmd_opts.hypernetwork_dir]
diff --git a/modules/ui_extra_networks_textual_inversion.py b/modules/ui_extra_networks_textual_inversion.py index 73134698..1b334fda 100644 --- a/modules/ui_extra_networks_textual_inversion.py +++ b/modules/ui_extra_networks_textual_inversion.py @@ -14,22 +14,29 @@ class ExtraNetworksPageTextualInversion(ui_extra_networks.ExtraNetworksPage): def create_item(self, name, index=None, enable_filter=True):
embedding = sd_hijack.model_hijack.embedding_db.word_embeddings.get(name)
+ if embedding is None:
+ return
path, ext = os.path.splitext(embedding.filename)
return {
"name": name,
"filename": embedding.filename,
+ "shorthash": embedding.shorthash,
"preview": self.find_preview(path),
"description": self.find_description(path),
- "search_term": self.search_terms_from_path(embedding.filename),
+ "search_term": self.search_terms_from_path(embedding.filename) + " " + (embedding.hash or ""),
"prompt": quote_js(embedding.name),
"local_preview": f"{path}.preview.{shared.opts.samples_format}",
"sort_keys": {'default': index, **self.get_sort_keys(embedding.filename)},
}
def list_items(self):
- for index, name in enumerate(sd_hijack.model_hijack.embedding_db.word_embeddings):
- yield self.create_item(name, index)
+ # instantiate a list to protect against concurrent modification
+ names = list(sd_hijack.model_hijack.embedding_db.word_embeddings)
+ for index, name in enumerate(names):
+ item = self.create_item(name, index)
+ if item is not None:
+ yield item
def allowed_directories_for_previews(self):
return list(sd_hijack.model_hijack.embedding_db.embedding_dirs)
diff --git a/modules/ui_extra_networks_user_metadata.py b/modules/ui_extra_networks_user_metadata.py index cda471e4..bfec140c 100644 --- a/modules/ui_extra_networks_user_metadata.py +++ b/modules/ui_extra_networks_user_metadata.py @@ -5,7 +5,7 @@ import os.path import gradio as gr
-from modules import generation_parameters_copypaste, images, sysinfo, errors
+from modules import generation_parameters_copypaste, images, sysinfo, errors, ui_extra_networks
class UserMetadataEditor:
@@ -89,15 +89,24 @@ class UserMetadataEditor: return preview
+ def relative_path(self, path):
+ for parent_path in self.page.allowed_directories_for_previews():
+ if ui_extra_networks.path_is_parent(parent_path, path):
+ return os.path.relpath(path, parent_path)
+
+ return os.path.basename(path)
+
def get_metadata_table(self, name):
item = self.page.items.get(name, {})
try:
filename = item["filename"]
+ shorthash = item.get("shorthash", None)
stats = os.stat(filename)
params = [
- ('Filename: ', os.path.basename(filename)),
+ ('Filename: ', self.relative_path(filename)),
('File size: ', sysinfo.pretty_bytes(stats.st_size)),
+ ('Hash: ', shorthash),
('Modified: ', datetime.datetime.fromtimestamp(stats.st_mtime).strftime('%Y-%m-%d %H:%M')),
]
@@ -115,7 +124,7 @@ class UserMetadataEditor: errors.display(e, f"reading metadata info for {name}")
params = []
- table = '<table class="file-metadata">' + "".join(f"<tr><th>{name}</th><td>{value}</td></tr>" for name, value in params) + '</table>'
+ table = '<table class="file-metadata">' + "".join(f"<tr><th>{name}</th><td>{value}</td></tr>" for name, value in params if value is not None) + '</table>'
return html.escape(name), user_metadata.get('description', ''), table, self.get_card_html(name), user_metadata.get('notes', '')
diff --git a/modules/ui_gradio_extensions.py b/modules/ui_gradio_extensions.py index b824b113..0d368f8b 100644 --- a/modules/ui_gradio_extensions.py +++ b/modules/ui_gradio_extensions.py @@ -2,12 +2,12 @@ import os import gradio as gr
from modules import localization, shared, scripts
-from modules.paths import script_path, data_path
+from modules.paths import script_path, data_path, cwd
def webpath(fn):
- if fn.startswith(script_path):
- web_path = os.path.relpath(fn, script_path).replace('\\', '/')
+ if fn.startswith(cwd):
+ web_path = os.path.relpath(fn, cwd)
else:
web_path = os.path.abspath(fn)
diff --git a/modules/ui_loadsave.py b/modules/ui_loadsave.py index a96c71b2..eb20ff25 100644 --- a/modules/ui_loadsave.py +++ b/modules/ui_loadsave.py @@ -4,7 +4,11 @@ import os import gradio as gr
from modules import errors
-from modules.ui_components import ToolButton
+from modules.ui_components import ToolButton, InputAccordion
+
+
+def radio_choices(comp): # gradio 3.41 changes choices from list of values to list of pairs
+ return [x[0] if isinstance(x, tuple) else x for x in getattr(comp, 'choices', [])]
class UiLoadsave:
@@ -37,31 +41,35 @@ class UiLoadsave: key = f"{path}/{field}"
if getattr(obj, 'custom_script_source', None) is not None:
- key = f"customscript/{obj.custom_script_source}/{key}"
+ key = f"customscript/{obj.custom_script_source}/{key}"
if getattr(obj, 'do_not_save_to_config', False):
return
saved_value = self.ui_settings.get(key, None)
+
+ if isinstance(obj, gr.Accordion) and isinstance(x, InputAccordion) and field == 'value':
+ field = 'open'
+
if saved_value is None:
self.ui_settings[key] = getattr(obj, field)
elif condition and not condition(saved_value):
pass
else:
- if isinstance(x, gr.Textbox) and field == 'value': # due to an undersirable behavior of gr.Textbox, if you give it an int value instead of str, everything dies
+ if isinstance(obj, gr.Textbox) and field == 'value': # due to an undesirable behavior of gr.Textbox, if you give it an int value instead of str, everything dies
saved_value = str(saved_value)
- elif isinstance(x, gr.Number) and field == 'value':
+ elif isinstance(obj, gr.Number) and field == 'value':
try:
saved_value = float(saved_value)
except ValueError:
- saved_value = -1
+ return
setattr(obj, field, saved_value)
if init_field is not None:
init_field(saved_value)
if field == 'value' and key not in self.component_mapping:
- self.component_mapping[key] = x
+ self.component_mapping[key] = obj
if type(x) in [gr.Slider, gr.Radio, gr.Checkbox, gr.Textbox, gr.Number, gr.Dropdown, ToolButton, gr.Button] and x.visible:
apply_field(x, 'visible')
@@ -73,7 +81,7 @@ class UiLoadsave: apply_field(x, 'step')
if type(x) == gr.Radio:
- apply_field(x, 'value', lambda val: val in x.choices)
+ apply_field(x, 'value', lambda val: val in radio_choices(x))
if type(x) == gr.Checkbox:
apply_field(x, 'value')
@@ -86,13 +94,20 @@ class UiLoadsave: if type(x) == gr.Dropdown:
def check_dropdown(val):
+ choices = radio_choices(x)
if getattr(x, 'multiselect', False):
- return all(value in x.choices for value in val)
+ return all(value in choices for value in val)
else:
- return val in x.choices
+ return val in choices
apply_field(x, 'value', check_dropdown, getattr(x, 'init_field', None))
+ if type(x) == InputAccordion:
+ if x.accordion.visible:
+ apply_field(x.accordion, 'visible')
+ apply_field(x, 'value')
+ apply_field(x.accordion, 'value')
+
def check_tab_id(tab_id):
tab_items = list(filter(lambda e: isinstance(e, gr.TabItem), x.children))
if type(tab_id) == str:
@@ -146,12 +161,14 @@ class UiLoadsave: for (path, component), new_value in zip(self.component_mapping.items(), values):
old_value = current_ui_settings.get(path)
- choices = getattr(component, 'choices', None)
+ choices = radio_choices(component)
if isinstance(new_value, int) and choices:
if new_value >= len(choices):
continue
new_value = choices[new_value]
+ if isinstance(new_value, tuple):
+ new_value = new_value[0]
if new_value == old_value:
continue
diff --git a/modules/ui_prompt_styles.py b/modules/ui_prompt_styles.py index 85eb3a64..0d74c23f 100644 --- a/modules/ui_prompt_styles.py +++ b/modules/ui_prompt_styles.py @@ -4,6 +4,7 @@ from modules import shared, ui_common, ui_components, styles styles_edit_symbol = '\U0001f58c\uFE0F' # 🖌️
styles_materialize_symbol = '\U0001f4cb' # 📋
+styles_copy_symbol = '\U0001f4dd' # 📝
def select_style(name):
@@ -52,6 +53,8 @@ def refresh_styles(): class UiPromptStyles:
def __init__(self, tabname, main_ui_prompt, main_ui_negative_prompt):
self.tabname = tabname
+ self.main_ui_prompt = main_ui_prompt
+ self.main_ui_negative_prompt = main_ui_negative_prompt
with gr.Row(elem_id=f"{tabname}_styles_row"):
self.dropdown = gr.Dropdown(label="Styles", show_label=False, elem_id=f"{tabname}_styles", choices=list(shared.prompt_styles.styles), value=[], multiselect=True, tooltip="Styles")
@@ -61,13 +64,14 @@ class UiPromptStyles: with gr.Row():
self.selection = gr.Dropdown(label="Styles", elem_id=f"{tabname}_styles_edit_select", choices=list(shared.prompt_styles.styles), value=[], allow_custom_value=True, info="Styles allow you to add custom text to prompt. Use the {prompt} token in style text, and it will be replaced with user's prompt when applying style. Otherwise, style's text will be added to the end of the prompt.")
ui_common.create_refresh_button([self.dropdown, self.selection], shared.prompt_styles.reload, lambda: {"choices": list(shared.prompt_styles.styles)}, f"refresh_{tabname}_styles")
- self.materialize = ui_components.ToolButton(value=styles_materialize_symbol, elem_id=f"{tabname}_style_apply", tooltip="Apply all selected styles from the style selction dropdown in main UI to the prompt.")
+ self.materialize = ui_components.ToolButton(value=styles_materialize_symbol, elem_id=f"{tabname}_style_apply_dialog", tooltip="Apply all selected styles from the style selction dropdown in main UI to the prompt.")
+ self.copy = ui_components.ToolButton(value=styles_copy_symbol, elem_id=f"{tabname}_style_copy", tooltip="Copy main UI prompt to style.")
with gr.Row():
- self.prompt = gr.Textbox(label="Prompt", show_label=True, elem_id=f"{tabname}_edit_style_prompt", lines=3)
+ self.prompt = gr.Textbox(label="Prompt", show_label=True, elem_id=f"{tabname}_edit_style_prompt", lines=3, elem_classes=["prompt"])
with gr.Row():
- self.neg_prompt = gr.Textbox(label="Negative prompt", show_label=True, elem_id=f"{tabname}_edit_style_neg_prompt", lines=3)
+ self.neg_prompt = gr.Textbox(label="Negative prompt", show_label=True, elem_id=f"{tabname}_edit_style_neg_prompt", lines=3, elem_classes=["prompt"])
with gr.Row():
self.save = gr.Button('Save', variant='primary', elem_id=f'{tabname}_edit_style_save', visible=False)
@@ -96,15 +100,21 @@ class UiPromptStyles: show_progress=False,
).then(refresh_styles, outputs=[self.dropdown, self.selection], show_progress=False)
- self.materialize.click(
- fn=materialize_styles,
- inputs=[main_ui_prompt, main_ui_negative_prompt, self.dropdown],
- outputs=[main_ui_prompt, main_ui_negative_prompt, self.dropdown],
+ self.setup_apply_button(self.materialize)
+
+ self.copy.click(
+ fn=lambda p, n: (p, n),
+ inputs=[main_ui_prompt, main_ui_negative_prompt],
+ outputs=[self.prompt, self.neg_prompt],
show_progress=False,
- ).then(fn=None, _js="function(){update_"+tabname+"_tokens(); closePopup();}", show_progress=False)
+ )
ui_common.setup_dialog(button_show=edit_button, dialog=styles_dialog, button_close=self.close)
-
-
-
+ def setup_apply_button(self, button):
+ button.click(
+ fn=materialize_styles,
+ inputs=[self.main_ui_prompt, self.main_ui_negative_prompt, self.dropdown],
+ outputs=[self.main_ui_prompt, self.main_ui_negative_prompt, self.dropdown],
+ show_progress=False,
+ ).then(fn=None, _js="function(){update_"+self.tabname+"_tokens(); closePopup();}", show_progress=False)
diff --git a/modules/ui_settings.py b/modules/ui_settings.py index 6dde4b6a..e054d00a 100644 --- a/modules/ui_settings.py +++ b/modules/ui_settings.py @@ -1,10 +1,11 @@ import gradio as gr
-from modules import ui_common, shared, script_callbacks, scripts, sd_models, sysinfo
+from modules import ui_common, shared, script_callbacks, scripts, sd_models, sysinfo, timer
from modules.call_queue import wrap_gradio_call
from modules.shared import opts
from modules.ui_components import FormRow
from modules.ui_gradio_extensions import reload_javascript
+from concurrent.futures import ThreadPoolExecutor, as_completed
def get_value_for_setting(key):
@@ -63,6 +64,9 @@ class UiSettings: quicksettings_list = None
quicksettings_names = None
text_settings = None
+ show_all_pages = None
+ show_one_page = None
+ search_input = None
def run_settings(self, *args):
changed = []
@@ -87,7 +91,7 @@ class UiSettings: if not opts.same_type(value, opts.data_labels[key].default):
return gr.update(visible=True), opts.dumpjson()
- if not opts.set(key, value):
+ if value is None or not opts.set(key, value):
return gr.update(value=getattr(opts, key)), opts.dumpjson()
opts.save(shared.config_filename)
@@ -135,7 +139,7 @@ class UiSettings: gr.Group()
current_tab = gr.TabItem(elem_id=f"settings_{elem_id}", label=text)
current_tab.__enter__()
- current_row = gr.Column(variant='compact')
+ current_row = gr.Column(elem_id=f"column_settings_{elem_id}", variant='compact')
current_row.__enter__()
previous_section = item.section
@@ -173,26 +177,43 @@ class UiSettings: download_localization = gr.Button(value='Download localization template', elem_id="download_localization")
reload_script_bodies = gr.Button(value='Reload custom script bodies (No ui updates, No restart)', variant='secondary', elem_id="settings_reload_script_bodies")
with gr.Row():
- unload_sd_model = gr.Button(value='Unload SD checkpoint to free VRAM', elem_id="sett_unload_sd_model")
- reload_sd_model = gr.Button(value='Reload the last SD checkpoint back into VRAM', elem_id="sett_reload_sd_model")
+ unload_sd_model = gr.Button(value='Unload SD checkpoint to RAM', elem_id="sett_unload_sd_model")
+ reload_sd_model = gr.Button(value='Load SD checkpoint to VRAM from RAM', elem_id="sett_reload_sd_model")
+ with gr.Row():
+ calculate_all_checkpoint_hash = gr.Button(value='Calculate hash for all checkpoint', elem_id="calculate_all_checkpoint_hash")
+ calculate_all_checkpoint_hash_threads = gr.Number(value=1, label="Number of parallel calculations", elem_id="calculate_all_checkpoint_hash_threads", precision=0, minimum=1)
with gr.TabItem("Licenses", id="licenses", elem_id="settings_tab_licenses"):
gr.HTML(shared.html("licenses.html"), elem_id="licenses")
- gr.Button(value="Show all pages", elem_id="settings_show_all_pages")
+ self.show_all_pages = gr.Button(value="Show all pages", elem_id="settings_show_all_pages")
+ self.show_one_page = gr.Button(value="Show only one page", elem_id="settings_show_one_page", visible=False)
+ self.show_one_page.click(lambda: None)
+
+ self.search_input = gr.Textbox(value="", elem_id="settings_search", max_lines=1, placeholder="Search...", show_label=False)
self.text_settings = gr.Textbox(elem_id="settings_json", value=lambda: opts.dumpjson(), visible=False)
+ def call_func_and_return_text(func, text):
+ def handler():
+ t = timer.Timer()
+ func()
+ t.record(text)
+
+ return f'{text} in {t.total:.1f}s'
+
+ return handler
+
unload_sd_model.click(
- fn=sd_models.unload_model_weights,
+ fn=call_func_and_return_text(sd_models.unload_model_weights, 'Unloaded the checkpoint'),
inputs=[],
- outputs=[]
+ outputs=[self.result]
)
reload_sd_model.click(
- fn=sd_models.reload_model_weights,
+ fn=call_func_and_return_text(lambda: sd_models.send_model_to_device(shared.sd_model), 'Loaded the checkpoint'),
inputs=[],
- outputs=[]
+ outputs=[self.result]
)
request_notifications.click(
@@ -241,6 +262,21 @@ class UiSettings: outputs=[sysinfo_check_output],
)
+ def calculate_all_checkpoint_hash_fn(max_thread):
+ checkpoints_list = sd_models.checkpoints_list.values()
+ with ThreadPoolExecutor(max_workers=max_thread) as executor:
+ futures = [executor.submit(checkpoint.calculate_shorthash) for checkpoint in checkpoints_list]
+ completed = 0
+ for _ in as_completed(futures):
+ completed += 1
+ print(f"{completed} / {len(checkpoints_list)} ")
+ print("Finish calculating hash for all checkpoints")
+
+ calculate_all_checkpoint_hash.click(
+ fn=calculate_all_checkpoint_hash_fn,
+ inputs=[calculate_all_checkpoint_hash_threads],
+ )
+
self.interface = settings_interface
def add_quicksettings(self):
@@ -294,3 +330,8 @@ class UiSettings: outputs=[self.component_dict[k] for k in component_keys],
queue=False,
)
+
+ def search(self, text):
+ print(text)
+
+ return [gr.update(visible=text in (comp.label or "")) for comp in self.components]
diff --git a/modules/ui_tempdir.py b/modules/ui_tempdir.py index 506017e5..85015db5 100644 --- a/modules/ui_tempdir.py +++ b/modules/ui_tempdir.py @@ -44,6 +44,8 @@ def save_pil_to_file(self, pil_image, dir=None, format="png"): if shared.opts.temp_dir != "":
dir = shared.opts.temp_dir
+ else:
+ os.makedirs(dir, exist_ok=True)
use_metadata = False
metadata = PngImagePlugin.PngInfo()
diff --git a/modules/ui_toprow.py b/modules/ui_toprow.py new file mode 100644 index 00000000..985b5a2d --- /dev/null +++ b/modules/ui_toprow.py @@ -0,0 +1,141 @@ +import gradio as gr
+
+from modules import shared, ui_prompt_styles
+import modules.images
+
+from modules.ui_components import ToolButton
+
+
+class Toprow:
+ """Creates a top row UI with prompts, generate button, styles, extra little buttons for things, and enables some functionality related to their operation"""
+
+ prompt = None
+ prompt_img = None
+ negative_prompt = None
+
+ button_interrogate = None
+ button_deepbooru = None
+
+ interrupt = None
+ skip = None
+ submit = None
+
+ paste = None
+ clear_prompt_button = None
+ apply_styles = None
+ restore_progress_button = None
+
+ token_counter = None
+ token_button = None
+ negative_token_counter = None
+ negative_token_button = None
+
+ ui_styles = None
+
+ submit_box = None
+
+ def __init__(self, is_img2img, is_compact=False):
+ id_part = "img2img" if is_img2img else "txt2img"
+ self.id_part = id_part
+ self.is_img2img = is_img2img
+ self.is_compact = is_compact
+
+ if not is_compact:
+ with gr.Row(elem_id=f"{id_part}_toprow", variant="compact"):
+ self.create_classic_toprow()
+ else:
+ self.create_submit_box()
+
+ def create_classic_toprow(self):
+ self.create_prompts()
+
+ with gr.Column(scale=1, elem_id=f"{self.id_part}_actions_column"):
+ self.create_submit_box()
+
+ self.create_tools_row()
+
+ self.create_styles_ui()
+
+ def create_inline_toprow_prompts(self):
+ if not self.is_compact:
+ return
+
+ self.create_prompts()
+
+ with gr.Row(elem_classes=["toprow-compact-stylerow"]):
+ with gr.Column(elem_classes=["toprow-compact-tools"]):
+ self.create_tools_row()
+ with gr.Column():
+ self.create_styles_ui()
+
+ def create_inline_toprow_image(self):
+ if not self.is_compact:
+ return
+
+ self.submit_box.render()
+
+ def create_prompts(self):
+ with gr.Column(elem_id=f"{self.id_part}_prompt_container", elem_classes=["prompt-container-compact"] if self.is_compact else [], scale=6):
+ with gr.Row(elem_id=f"{self.id_part}_prompt_row", elem_classes=["prompt-row"]):
+ self.prompt = gr.Textbox(label="Prompt", elem_id=f"{self.id_part}_prompt", show_label=False, lines=3, placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
+ self.prompt_img = gr.File(label="", elem_id=f"{self.id_part}_prompt_image", file_count="single", type="binary", visible=False)
+
+ with gr.Row(elem_id=f"{self.id_part}_neg_prompt_row", elem_classes=["prompt-row"]):
+ self.negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{self.id_part}_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
+
+ self.prompt_img.change(
+ fn=modules.images.image_data,
+ inputs=[self.prompt_img],
+ outputs=[self.prompt, self.prompt_img],
+ show_progress=False,
+ )
+
+ def create_submit_box(self):
+ with gr.Row(elem_id=f"{self.id_part}_generate_box", elem_classes=["generate-box"] + (["generate-box-compact"] if self.is_compact else []), render=not self.is_compact) as submit_box:
+ self.submit_box = submit_box
+
+ self.interrupt = gr.Button('Interrupt', elem_id=f"{self.id_part}_interrupt", elem_classes="generate-box-interrupt")
+ self.skip = gr.Button('Skip', elem_id=f"{self.id_part}_skip", elem_classes="generate-box-skip")
+ self.submit = gr.Button('Generate', elem_id=f"{self.id_part}_generate", variant='primary')
+
+ self.skip.click(
+ fn=lambda: shared.state.skip(),
+ inputs=[],
+ outputs=[],
+ )
+
+ self.interrupt.click(
+ fn=lambda: shared.state.interrupt(),
+ inputs=[],
+ outputs=[],
+ )
+
+ def create_tools_row(self):
+ with gr.Row(elem_id=f"{self.id_part}_tools"):
+ from modules.ui import paste_symbol, clear_prompt_symbol, restore_progress_symbol
+
+ self.paste = ToolButton(value=paste_symbol, elem_id="paste", tooltip="Read generation parameters from prompt or last generation if prompt is empty into user interface.")
+ self.clear_prompt_button = ToolButton(value=clear_prompt_symbol, elem_id=f"{self.id_part}_clear_prompt", tooltip="Clear prompt")
+ self.apply_styles = ToolButton(value=ui_prompt_styles.styles_materialize_symbol, elem_id=f"{self.id_part}_style_apply", tooltip="Apply all selected styles to prompts.")
+
+ if self.is_img2img:
+ self.button_interrogate = ToolButton('📎', tooltip='Interrogate CLIP - use CLIP neural network to create a text describing the image, and put it into the prompt field', elem_id="interrogate")
+ self.button_deepbooru = ToolButton('📦', tooltip='Interrogate DeepBooru - use DeepBooru neural network to create a text describing the image, and put it into the prompt field', elem_id="deepbooru")
+
+ self.restore_progress_button = ToolButton(value=restore_progress_symbol, elem_id=f"{self.id_part}_restore_progress", visible=False, tooltip="Restore progress")
+
+ self.token_counter = gr.HTML(value="<span>0/75</span>", elem_id=f"{self.id_part}_token_counter", elem_classes=["token-counter"])
+ self.token_button = gr.Button(visible=False, elem_id=f"{self.id_part}_token_button")
+ self.negative_token_counter = gr.HTML(value="<span>0/75</span>", elem_id=f"{self.id_part}_negative_token_counter", elem_classes=["token-counter"])
+ self.negative_token_button = gr.Button(visible=False, elem_id=f"{self.id_part}_negative_token_button")
+
+ self.clear_prompt_button.click(
+ fn=lambda *x: x,
+ _js="confirm_clear_prompt",
+ inputs=[self.prompt, self.negative_prompt],
+ outputs=[self.prompt, self.negative_prompt],
+ )
+
+ def create_styles_ui(self):
+ self.ui_styles = ui_prompt_styles.UiPromptStyles(self.id_part, self.prompt, self.negative_prompt)
+ self.ui_styles.setup_apply_button(self.apply_styles)
diff --git a/modules/xlmr_m18.py b/modules/xlmr_m18.py new file mode 100644 index 00000000..a727e865 --- /dev/null +++ b/modules/xlmr_m18.py @@ -0,0 +1,164 @@ +from transformers import BertPreTrainedModel,BertConfig +import torch.nn as nn +import torch +from transformers.models.xlm_roberta.configuration_xlm_roberta import XLMRobertaConfig +from transformers import XLMRobertaModel,XLMRobertaTokenizer +from typing import Optional + +class BertSeriesConfig(BertConfig): + def __init__(self, vocab_size=30522, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act="gelu", hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, pad_token_id=0, position_embedding_type="absolute", use_cache=True, classifier_dropout=None,project_dim=512, pooler_fn="average",learn_encoder=False,model_type='bert',**kwargs): + + super().__init__(vocab_size, hidden_size, num_hidden_layers, num_attention_heads, intermediate_size, hidden_act, hidden_dropout_prob, attention_probs_dropout_prob, max_position_embeddings, type_vocab_size, initializer_range, layer_norm_eps, pad_token_id, position_embedding_type, use_cache, classifier_dropout, **kwargs) + self.project_dim = project_dim + self.pooler_fn = pooler_fn + self.learn_encoder = learn_encoder + +class RobertaSeriesConfig(XLMRobertaConfig): + def __init__(self, pad_token_id=1, bos_token_id=0, eos_token_id=2,project_dim=512,pooler_fn='cls',learn_encoder=False, **kwargs): + super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs) + self.project_dim = project_dim + self.pooler_fn = pooler_fn + self.learn_encoder = learn_encoder + + +class BertSeriesModelWithTransformation(BertPreTrainedModel): + + _keys_to_ignore_on_load_unexpected = [r"pooler"] + _keys_to_ignore_on_load_missing = [r"position_ids", r"predictions.decoder.bias"] + config_class = BertSeriesConfig + + def __init__(self, config=None, **kargs): + # modify initialization for autoloading + if config is None: + config = XLMRobertaConfig() + config.attention_probs_dropout_prob= 0.1 + config.bos_token_id=0 + config.eos_token_id=2 + config.hidden_act='gelu' + config.hidden_dropout_prob=0.1 + config.hidden_size=1024 + config.initializer_range=0.02 + config.intermediate_size=4096 + config.layer_norm_eps=1e-05 + config.max_position_embeddings=514 + + config.num_attention_heads=16 + config.num_hidden_layers=24 + config.output_past=True + config.pad_token_id=1 + config.position_embedding_type= "absolute" + + config.type_vocab_size= 1 + config.use_cache=True + config.vocab_size= 250002 + config.project_dim = 1024 + config.learn_encoder = False + super().__init__(config) + self.roberta = XLMRobertaModel(config) + self.transformation = nn.Linear(config.hidden_size,config.project_dim) + # self.pre_LN=nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) + self.tokenizer = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large') + # self.pooler = lambda x: x[:,0] + # self.post_init() + + self.has_pre_transformation = True + if self.has_pre_transformation: + self.transformation_pre = nn.Linear(config.hidden_size, config.project_dim) + self.pre_LN = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) + self.post_init() + + def encode(self,c): + device = next(self.parameters()).device + text = self.tokenizer(c, + truncation=True, + max_length=77, + return_length=False, + return_overflowing_tokens=False, + padding="max_length", + return_tensors="pt") + text["input_ids"] = torch.tensor(text["input_ids"]).to(device) + text["attention_mask"] = torch.tensor( + text['attention_mask']).to(device) + features = self(**text) + return features['projection_state'] + + def forward( + self, + input_ids: Optional[torch.Tensor] = None, + attention_mask: Optional[torch.Tensor] = None, + token_type_ids: Optional[torch.Tensor] = None, + position_ids: Optional[torch.Tensor] = None, + head_mask: Optional[torch.Tensor] = None, + inputs_embeds: Optional[torch.Tensor] = None, + encoder_hidden_states: Optional[torch.Tensor] = None, + encoder_attention_mask: Optional[torch.Tensor] = None, + output_attentions: Optional[bool] = None, + return_dict: Optional[bool] = None, + output_hidden_states: Optional[bool] = None, + ) : + r""" + """ + + return_dict = return_dict if return_dict is not None else self.config.use_return_dict + + + outputs = self.roberta( + input_ids=input_ids, + attention_mask=attention_mask, + token_type_ids=token_type_ids, + position_ids=position_ids, + head_mask=head_mask, + inputs_embeds=inputs_embeds, + encoder_hidden_states=encoder_hidden_states, + encoder_attention_mask=encoder_attention_mask, + output_attentions=output_attentions, + output_hidden_states=True, + return_dict=return_dict, + ) + + # # last module outputs + # sequence_output = outputs[0] + + + # # project every module + # sequence_output_ln = self.pre_LN(sequence_output) + + # # pooler + # pooler_output = self.pooler(sequence_output_ln) + # pooler_output = self.transformation(pooler_output) + # projection_state = self.transformation(outputs.last_hidden_state) + + if self.has_pre_transformation: + sequence_output2 = outputs["hidden_states"][-2] + sequence_output2 = self.pre_LN(sequence_output2) + projection_state2 = self.transformation_pre(sequence_output2) + + return { + "projection_state": projection_state2, + "last_hidden_state": outputs.last_hidden_state, + "hidden_states": outputs.hidden_states, + "attentions": outputs.attentions, + } + else: + projection_state = self.transformation(outputs.last_hidden_state) + return { + "projection_state": projection_state, + "last_hidden_state": outputs.last_hidden_state, + "hidden_states": outputs.hidden_states, + "attentions": outputs.attentions, + } + + + # return { + # 'pooler_output':pooler_output, + # 'last_hidden_state':outputs.last_hidden_state, + # 'hidden_states':outputs.hidden_states, + # 'attentions':outputs.attentions, + # 'projection_state':projection_state, + # 'sequence_out': sequence_output + # } + + +class RobertaSeriesModelWithTransformation(BertSeriesModelWithTransformation): + base_model_prefix = 'roberta' + config_class= RobertaSeriesConfig diff --git a/requirements.txt b/requirements.txt index d83092f0..80b43845 100644 --- a/requirements.txt +++ b/requirements.txt @@ -8,7 +8,7 @@ clean-fid einops
fastapi>=0.90.1
gfpgan
-gradio==3.39.0
+gradio==3.41.2
inflection
jsonmerge
kornia
diff --git a/requirements_versions.txt b/requirements_versions.txt index dec45df3..cb7403a9 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -7,7 +7,7 @@ clean-fid==0.1.35 einops==0.4.1
fastapi==0.94.0
gfpgan==1.3.8
-gradio==3.39.0
+gradio==3.41.2
httpcore==0.15
inflection==0.5.1
jsonmerge==1.8.0
@@ -27,5 +27,6 @@ timm==0.9.2 tomesd==0.1.3
torch
torchdiffeq==0.2.3
-torchsde==0.2.5
+torchsde==0.2.6
transformers==4.30.2
+httpx==0.24.1
@@ -124,16 +124,29 @@ document.addEventListener("DOMContentLoaded", function() { * Add a ctrl+enter as a shortcut to start a generation */ document.addEventListener('keydown', function(e) { - var handled = false; - if (e.key !== undefined) { - if ((e.key == "Enter" && (e.metaKey || e.ctrlKey || e.altKey))) handled = true; - } else if (e.keyCode !== undefined) { - if ((e.keyCode == 13 && (e.metaKey || e.ctrlKey || e.altKey))) handled = true; - } - if (handled) { - var button = get_uiCurrentTabContent().querySelector('button[id$=_generate]'); - if (button) { - button.click(); + const isEnter = e.key === 'Enter' || e.keyCode === 13; + const isModifierKey = e.metaKey || e.ctrlKey || e.altKey; + + const interruptButton = get_uiCurrentTabContent().querySelector('button[id$=_interrupt]'); + const generateButton = get_uiCurrentTabContent().querySelector('button[id$=_generate]'); + + if (isEnter && isModifierKey) { + if (interruptButton.style.display === 'block') { + interruptButton.click(); + const callback = (mutationList) => { + for (const mutation of mutationList) { + if (mutation.type === 'attributes' && mutation.attributeName === 'style') { + if (interruptButton.style.display === 'none') { + generateButton.click(); + observer.disconnect(); + } + } + } + }; + const observer = new MutationObserver(callback); + observer.observe(interruptButton, {attributes: true}); + } else { + generateButton.click(); } e.preventDefault(); } diff --git a/scripts/postprocessing_upscale.py b/scripts/postprocessing_upscale.py index edb70ac0..eb42a29e 100644 --- a/scripts/postprocessing_upscale.py +++ b/scripts/postprocessing_upscale.py @@ -29,7 +29,7 @@ class ScriptPostprocessingUpscale(scripts_postprocessing.ScriptPostprocessing): upscaling_resize_w = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="extras_upscaling_resize_w")
upscaling_resize_h = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="extras_upscaling_resize_h")
with gr.Column(elem_id="upscaling_dimensions_row", scale=1, elem_classes="dimensions-tools"):
- upscaling_res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="upscaling_res_switch_btn")
+ upscaling_res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="upscaling_res_switch_btn", tooltip="Switch width/height")
upscaling_crop = gr.Checkbox(label='Crop to fit', value=True, elem_id="extras_upscaling_crop")
with FormRow():
diff --git a/scripts/prompts_from_file.py b/scripts/prompts_from_file.py index 50320d55..a4a2f24d 100644 --- a/scripts/prompts_from_file.py +++ b/scripts/prompts_from_file.py @@ -5,11 +5,17 @@ import shlex import modules.scripts as scripts
import gradio as gr
-from modules import sd_samplers, errors
+from modules import sd_samplers, errors, sd_models
from modules.processing import Processed, process_images
from modules.shared import state
+def process_model_tag(tag):
+ info = sd_models.get_closet_checkpoint_match(tag)
+ assert info is not None, f'Unknown checkpoint: {tag}'
+ return info.name
+
+
def process_string_tag(tag):
return tag
@@ -27,7 +33,7 @@ def process_boolean_tag(tag): prompt_tags = {
- "sd_model": None,
+ "sd_model": process_model_tag,
"outpath_samples": process_string_tag,
"outpath_grids": process_string_tag,
"prompt_for_display": process_string_tag,
@@ -108,6 +114,7 @@ class Script(scripts.Script): def ui(self, is_img2img):
checkbox_iterate = gr.Checkbox(label="Iterate seed every line", value=False, elem_id=self.elem_id("checkbox_iterate"))
checkbox_iterate_batch = gr.Checkbox(label="Use same random seed for all lines", value=False, elem_id=self.elem_id("checkbox_iterate_batch"))
+ prompt_position = gr.Radio(["start", "end"], label="Insert prompts at the", elem_id=self.elem_id("prompt_position"), value="start")
prompt_txt = gr.Textbox(label="List of prompt inputs", lines=1, elem_id=self.elem_id("prompt_txt"))
file = gr.File(label="Upload prompt inputs", type='binary', elem_id=self.elem_id("file"))
@@ -118,9 +125,9 @@ class Script(scripts.Script): # We don't shrink back to 1, because that causes the control to ignore [enter], and it may
# be unclear to the user that shift-enter is needed.
prompt_txt.change(lambda tb: gr.update(lines=7) if ("\n" in tb) else gr.update(lines=2), inputs=[prompt_txt], outputs=[prompt_txt], show_progress=False)
- return [checkbox_iterate, checkbox_iterate_batch, prompt_txt]
+ return [checkbox_iterate, checkbox_iterate_batch, prompt_position, prompt_txt]
- def run(self, p, checkbox_iterate, checkbox_iterate_batch, prompt_txt: str):
+ def run(self, p, checkbox_iterate, checkbox_iterate_batch, prompt_position, prompt_txt: str):
lines = [x for x in (x.strip() for x in prompt_txt.splitlines()) if x]
p.do_not_save_grid = True
@@ -156,7 +163,22 @@ class Script(scripts.Script): copy_p = copy.copy(p)
for k, v in args.items():
- setattr(copy_p, k, v)
+ if k == "sd_model":
+ copy_p.override_settings['sd_model_checkpoint'] = v
+ else:
+ setattr(copy_p, k, v)
+
+ if args.get("prompt") and p.prompt:
+ if prompt_position == "start":
+ copy_p.prompt = args.get("prompt") + " " + p.prompt
+ else:
+ copy_p.prompt = p.prompt + " " + args.get("prompt")
+
+ if args.get("negative_prompt") and p.negative_prompt:
+ if prompt_position == "start":
+ copy_p.negative_prompt = args.get("negative_prompt") + " " + p.negative_prompt
+ else:
+ copy_p.negative_prompt = p.negative_prompt + " " + args.get("negative_prompt")
proc = process_images(copy_p)
images += proc.images
diff --git a/scripts/xyz_grid.py b/scripts/xyz_grid.py index d37b428f..0dc255bc 100644 --- a/scripts/xyz_grid.py +++ b/scripts/xyz_grid.py @@ -86,6 +86,15 @@ def confirm_checkpoints(p, xs): raise RuntimeError(f"Unknown checkpoint: {x}")
+def confirm_checkpoints_or_none(p, xs):
+ for x in xs:
+ if x in (None, "", "None", "none"):
+ continue
+
+ if modules.sd_models.get_closet_checkpoint_match(x) is None:
+ raise RuntimeError(f"Unknown checkpoint: {x}")
+
+
def apply_clip_skip(p, x, xs):
opts.data["CLIP_stop_at_last_layers"] = x
@@ -175,22 +184,35 @@ def do_nothing(p, x, xs): def format_nothing(p, opt, x):
return ""
+
def format_remove_path(p, opt, x):
return os.path.basename(x)
+
def str_permutations(x):
"""dummy function for specifying it in AxisOption's type when you want to get a list of permutations"""
return x
+def list_to_csv_string(data_list):
+ with StringIO() as o:
+ csv.writer(o).writerow(data_list)
+ return o.getvalue().strip()
+
+
+def csv_string_to_list_strip(data_str):
+ return list(map(str.strip, chain.from_iterable(csv.reader(StringIO(data_str)))))
+
+
class AxisOption:
- def __init__(self, label, type, apply, format_value=format_value_add_label, confirm=None, cost=0.0, choices=None):
+ def __init__(self, label, type, apply, format_value=format_value_add_label, confirm=None, cost=0.0, choices=None, prepare=None):
self.label = label
self.type = type
self.apply = apply
self.format_value = format_value
self.confirm = confirm
self.cost = cost
+ self.prepare = prepare
self.choices = choices
@@ -199,6 +221,7 @@ class AxisOptionImg2Img(AxisOption): super().__init__(*args, **kwargs)
self.is_img2img = True
+
class AxisOptionTxt2Img(AxisOption):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
@@ -216,9 +239,9 @@ axis_options = [ AxisOptionImg2Img("Image CFG Scale", float, apply_field("image_cfg_scale")),
AxisOption("Prompt S/R", str, apply_prompt, format_value=format_value),
AxisOption("Prompt order", str_permutations, apply_order, format_value=format_value_join_list),
- AxisOptionTxt2Img("Sampler", str, apply_field("sampler_name"), format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers]),
- AxisOptionTxt2Img("Hires sampler", str, apply_field("hr_sampler_name"), confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers_for_img2img]),
- AxisOptionImg2Img("Sampler", str, apply_field("sampler_name"), format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers_for_img2img]),
+ AxisOptionTxt2Img("Sampler", str, apply_field("sampler_name"), format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers if x.name not in opts.hide_samplers]),
+ AxisOptionTxt2Img("Hires sampler", str, apply_field("hr_sampler_name"), confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers_for_img2img if x.name not in opts.hide_samplers]),
+ AxisOptionImg2Img("Sampler", str, apply_field("sampler_name"), format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers_for_img2img if x.name not in opts.hide_samplers]),
AxisOption("Checkpoint name", str, apply_checkpoint, format_value=format_remove_path, confirm=confirm_checkpoints, cost=1.0, choices=lambda: sorted(sd_models.checkpoints_list, key=str.casefold)),
AxisOption("Negative Guidance minimum sigma", float, apply_field("s_min_uncond")),
AxisOption("Sigma Churn", float, apply_field("s_churn")),
@@ -232,6 +255,8 @@ axis_options = [ AxisOption("Eta", float, apply_field("eta")),
AxisOption("Clip skip", int, apply_clip_skip),
AxisOption("Denoising", float, apply_field("denoising_strength")),
+ AxisOption("Initial noise multiplier", float, apply_field("initial_noise_multiplier")),
+ AxisOption("Extra noise", float, apply_override("img2img_extra_noise")),
AxisOptionTxt2Img("Hires upscaler", str, apply_field("hr_upscaler"), choices=lambda: [*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]]),
AxisOptionImg2Img("Cond. Image Mask Weight", float, apply_field("inpainting_mask_weight")),
AxisOption("VAE", str, apply_vae, cost=0.7, choices=lambda: ['None'] + list(sd_vae.vae_dict)),
@@ -241,6 +266,10 @@ axis_options = [ AxisOption("Token merging ratio", float, apply_override('token_merging_ratio')),
AxisOption("Token merging ratio high-res", float, apply_override('token_merging_ratio_hr')),
AxisOption("Always discard next-to-last sigma", str, apply_override('always_discard_next_to_last_sigma', boolean=True), choices=boolean_choice(reverse=True)),
+ AxisOption("SGM noise multiplier", str, apply_override('sgm_noise_multiplier', boolean=True), choices=boolean_choice(reverse=True)),
+ AxisOption("Refiner checkpoint", str, apply_field('refiner_checkpoint'), format_value=format_remove_path, confirm=confirm_checkpoints_or_none, cost=1.0, choices=lambda: ['None'] + sorted(sd_models.checkpoints_list, key=str.casefold)),
+ AxisOption("Refiner switch at", float, apply_field('refiner_switch_at')),
+ AxisOption("RNG source", str, apply_override("randn_source"), choices=lambda: ["GPU", "CPU", "NV"]),
]
@@ -286,11 +315,10 @@ def draw_xyz_grid(p, xs, ys, zs, x_labels, y_labels, z_labels, cell, draw_legend cell_size = (processed_result.width, processed_result.height)
if processed_result.images[0] is not None:
cell_mode = processed_result.images[0].mode
- #This corrects size in case of batches:
+ # This corrects size in case of batches:
cell_size = processed_result.images[0].size
processed_result.images[idx] = Image.new(cell_mode, cell_size)
-
if first_axes_processed == 'x':
for ix, x in enumerate(xs):
if second_axes_processed == 'y':
@@ -348,9 +376,9 @@ def draw_xyz_grid(p, xs, ys, zs, x_labels, y_labels, z_labels, cell, draw_legend if draw_legend:
z_grid = images.draw_grid_annotations(z_grid, sub_grid_size[0], sub_grid_size[1], title_texts, [[images.GridAnnotation()]])
processed_result.images.insert(0, z_grid)
- #TODO: Deeper aspects of the program rely on grid info being misaligned between metadata arrays, which is not ideal.
- #processed_result.all_prompts.insert(0, processed_result.all_prompts[0])
- #processed_result.all_seeds.insert(0, processed_result.all_seeds[0])
+ # TODO: Deeper aspects of the program rely on grid info being misaligned between metadata arrays, which is not ideal.
+ # processed_result.all_prompts.insert(0, processed_result.all_prompts[0])
+ # processed_result.all_seeds.insert(0, processed_result.all_seeds[0])
processed_result.infotexts.insert(0, processed_result.infotexts[0])
return processed_result
@@ -374,8 +402,8 @@ class SharedSettingsStackHelper(object): re_range = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\(([+-]\d+)\s*\))?\s*")
re_range_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d*)?)(?:\s*\(([+-]\d+(?:.\d*)?)\s*\))?\s*")
-re_range_count = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\[(\d+)\s*\])?\s*")
-re_range_count_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d*)?)(?:\s*\[(\d+(?:.\d*)?)\s*\])?\s*")
+re_range_count = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\[(\d+)\s*])?\s*")
+re_range_count_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d*)?)(?:\s*\[(\d+(?:.\d*)?)\s*])?\s*")
class Script(scripts.Script):
@@ -390,19 +418,19 @@ class Script(scripts.Script): with gr.Row():
x_type = gr.Dropdown(label="X type", choices=[x.label for x in self.current_axis_options], value=self.current_axis_options[1].label, type="index", elem_id=self.elem_id("x_type"))
x_values = gr.Textbox(label="X values", lines=1, elem_id=self.elem_id("x_values"))
- x_values_dropdown = gr.Dropdown(label="X values",visible=False,multiselect=True,interactive=True)
+ x_values_dropdown = gr.Dropdown(label="X values", visible=False, multiselect=True, interactive=True)
fill_x_button = ToolButton(value=fill_values_symbol, elem_id="xyz_grid_fill_x_tool_button", visible=False)
with gr.Row():
y_type = gr.Dropdown(label="Y type", choices=[x.label for x in self.current_axis_options], value=self.current_axis_options[0].label, type="index", elem_id=self.elem_id("y_type"))
y_values = gr.Textbox(label="Y values", lines=1, elem_id=self.elem_id("y_values"))
- y_values_dropdown = gr.Dropdown(label="Y values",visible=False,multiselect=True,interactive=True)
+ y_values_dropdown = gr.Dropdown(label="Y values", visible=False, multiselect=True, interactive=True)
fill_y_button = ToolButton(value=fill_values_symbol, elem_id="xyz_grid_fill_y_tool_button", visible=False)
with gr.Row():
z_type = gr.Dropdown(label="Z type", choices=[x.label for x in self.current_axis_options], value=self.current_axis_options[0].label, type="index", elem_id=self.elem_id("z_type"))
z_values = gr.Textbox(label="Z values", lines=1, elem_id=self.elem_id("z_values"))
- z_values_dropdown = gr.Dropdown(label="Z values",visible=False,multiselect=True,interactive=True)
+ z_values_dropdown = gr.Dropdown(label="Z values", visible=False, multiselect=True, interactive=True)
fill_z_button = ToolButton(value=fill_values_symbol, elem_id="xyz_grid_fill_z_tool_button", visible=False)
with gr.Row(variant="compact", elem_id="axis_options"):
@@ -414,6 +442,8 @@ class Script(scripts.Script): include_sub_grids = gr.Checkbox(label='Include Sub Grids', value=False, elem_id=self.elem_id("include_sub_grids"))
with gr.Column():
margin_size = gr.Slider(label="Grid margins (px)", minimum=0, maximum=500, value=0, step=2, elem_id=self.elem_id("margin_size"))
+ with gr.Column():
+ csv_mode = gr.Checkbox(label='Use text inputs instead of dropdowns', value=False, elem_id=self.elem_id("csv_mode"))
with gr.Row(variant="compact", elem_id="swap_axes"):
swap_xy_axes_button = gr.Button(value="Swap X/Y axes", elem_id="xy_grid_swap_axes_button")
@@ -430,50 +460,71 @@ class Script(scripts.Script): xz_swap_args = [x_type, x_values, x_values_dropdown, z_type, z_values, z_values_dropdown]
swap_xz_axes_button.click(swap_axes, inputs=xz_swap_args, outputs=xz_swap_args)
- def fill(x_type):
- axis = self.current_axis_options[x_type]
- return axis.choices() if axis.choices else gr.update()
+ def fill(axis_type, csv_mode):
+ axis = self.current_axis_options[axis_type]
+ if axis.choices:
+ if csv_mode:
+ return list_to_csv_string(axis.choices()), gr.update()
+ else:
+ return gr.update(), axis.choices()
+ else:
+ return gr.update(), gr.update()
- fill_x_button.click(fn=fill, inputs=[x_type], outputs=[x_values_dropdown])
- fill_y_button.click(fn=fill, inputs=[y_type], outputs=[y_values_dropdown])
- fill_z_button.click(fn=fill, inputs=[z_type], outputs=[z_values_dropdown])
+ fill_x_button.click(fn=fill, inputs=[x_type, csv_mode], outputs=[x_values, x_values_dropdown])
+ fill_y_button.click(fn=fill, inputs=[y_type, csv_mode], outputs=[y_values, y_values_dropdown])
+ fill_z_button.click(fn=fill, inputs=[z_type, csv_mode], outputs=[z_values, z_values_dropdown])
- def select_axis(axis_type,axis_values_dropdown):
+ def select_axis(axis_type, axis_values, axis_values_dropdown, csv_mode):
choices = self.current_axis_options[axis_type].choices
has_choices = choices is not None
- current_values = axis_values_dropdown
+
if has_choices:
choices = choices()
- if isinstance(current_values,str):
- current_values = current_values.split(",")
- current_values = list(filter(lambda x: x in choices, current_values))
- return gr.Button.update(visible=has_choices),gr.Textbox.update(visible=not has_choices),gr.update(choices=choices if has_choices else None,visible=has_choices,value=current_values)
-
- x_type.change(fn=select_axis, inputs=[x_type,x_values_dropdown], outputs=[fill_x_button,x_values,x_values_dropdown])
- y_type.change(fn=select_axis, inputs=[y_type,y_values_dropdown], outputs=[fill_y_button,y_values,y_values_dropdown])
- z_type.change(fn=select_axis, inputs=[z_type,z_values_dropdown], outputs=[fill_z_button,z_values,z_values_dropdown])
-
- def get_dropdown_update_from_params(axis,params):
+ if csv_mode:
+ if axis_values_dropdown:
+ axis_values = list_to_csv_string(list(filter(lambda x: x in choices, axis_values_dropdown)))
+ axis_values_dropdown = []
+ else:
+ if axis_values:
+ axis_values_dropdown = list(filter(lambda x: x in choices, csv_string_to_list_strip(axis_values)))
+ axis_values = ""
+
+ return (gr.Button.update(visible=has_choices), gr.Textbox.update(visible=not has_choices or csv_mode, value=axis_values),
+ gr.update(choices=choices if has_choices else None, visible=has_choices and not csv_mode, value=axis_values_dropdown))
+
+ x_type.change(fn=select_axis, inputs=[x_type, x_values, x_values_dropdown, csv_mode], outputs=[fill_x_button, x_values, x_values_dropdown])
+ y_type.change(fn=select_axis, inputs=[y_type, y_values, y_values_dropdown, csv_mode], outputs=[fill_y_button, y_values, y_values_dropdown])
+ z_type.change(fn=select_axis, inputs=[z_type, z_values, z_values_dropdown, csv_mode], outputs=[fill_z_button, z_values, z_values_dropdown])
+
+ def change_choice_mode(csv_mode, x_type, x_values, x_values_dropdown, y_type, y_values, y_values_dropdown, z_type, z_values, z_values_dropdown):
+ _fill_x_button, _x_values, _x_values_dropdown = select_axis(x_type, x_values, x_values_dropdown, csv_mode)
+ _fill_y_button, _y_values, _y_values_dropdown = select_axis(y_type, y_values, y_values_dropdown, csv_mode)
+ _fill_z_button, _z_values, _z_values_dropdown = select_axis(z_type, z_values, z_values_dropdown, csv_mode)
+ return _fill_x_button, _x_values, _x_values_dropdown, _fill_y_button, _y_values, _y_values_dropdown, _fill_z_button, _z_values, _z_values_dropdown
+
+ csv_mode.change(fn=change_choice_mode, inputs=[csv_mode, x_type, x_values, x_values_dropdown, y_type, y_values, y_values_dropdown, z_type, z_values, z_values_dropdown], outputs=[fill_x_button, x_values, x_values_dropdown, fill_y_button, y_values, y_values_dropdown, fill_z_button, z_values, z_values_dropdown])
+
+ def get_dropdown_update_from_params(axis, params):
val_key = f"{axis} Values"
- vals = params.get(val_key,"")
- valslist = [x.strip() for x in chain.from_iterable(csv.reader(StringIO(vals))) if x]
- return gr.update(value = valslist)
+ vals = params.get(val_key, "")
+ valslist = csv_string_to_list_strip(vals)
+ return gr.update(value=valslist)
self.infotext_fields = (
(x_type, "X Type"),
(x_values, "X Values"),
- (x_values_dropdown, lambda params:get_dropdown_update_from_params("X",params)),
+ (x_values_dropdown, lambda params: get_dropdown_update_from_params("X", params)),
(y_type, "Y Type"),
(y_values, "Y Values"),
- (y_values_dropdown, lambda params:get_dropdown_update_from_params("Y",params)),
+ (y_values_dropdown, lambda params: get_dropdown_update_from_params("Y", params)),
(z_type, "Z Type"),
(z_values, "Z Values"),
- (z_values_dropdown, lambda params:get_dropdown_update_from_params("Z",params)),
+ (z_values_dropdown, lambda params: get_dropdown_update_from_params("Z", params)),
)
- return [x_type, x_values, x_values_dropdown, y_type, y_values, y_values_dropdown, z_type, z_values, z_values_dropdown, draw_legend, include_lone_images, include_sub_grids, no_fixed_seeds, margin_size]
+ return [x_type, x_values, x_values_dropdown, y_type, y_values, y_values_dropdown, z_type, z_values, z_values_dropdown, draw_legend, include_lone_images, include_sub_grids, no_fixed_seeds, margin_size, csv_mode]
- def run(self, p, x_type, x_values, x_values_dropdown, y_type, y_values, y_values_dropdown, z_type, z_values, z_values_dropdown, draw_legend, include_lone_images, include_sub_grids, no_fixed_seeds, margin_size):
+ def run(self, p, x_type, x_values, x_values_dropdown, y_type, y_values, y_values_dropdown, z_type, z_values, z_values_dropdown, draw_legend, include_lone_images, include_sub_grids, no_fixed_seeds, margin_size, csv_mode):
if not no_fixed_seeds:
modules.processing.fix_seed(p)
@@ -484,10 +535,12 @@ class Script(scripts.Script): if opt.label == 'Nothing':
return [0]
- if opt.choices is not None:
+ if opt.choices is not None and not csv_mode:
valslist = vals_dropdown
+ elif opt.prepare is not None:
+ valslist = opt.prepare(vals)
else:
- valslist = [x.strip() for x in chain.from_iterable(csv.reader(StringIO(vals))) if x]
+ valslist = csv_string_to_list_strip(vals)
if opt.type == int:
valslist_ext = []
@@ -503,8 +556,8 @@ class Script(scripts.Script): valslist_ext += list(range(start, end, step))
elif mc is not None:
start = int(mc.group(1))
- end = int(mc.group(2))
- num = int(mc.group(3)) if mc.group(3) is not None else 1
+ end = int(mc.group(2))
+ num = int(mc.group(3)) if mc.group(3) is not None else 1
valslist_ext += [int(x) for x in np.linspace(start=start, stop=end, num=num).tolist()]
else:
@@ -525,8 +578,8 @@ class Script(scripts.Script): valslist_ext += np.arange(start, end + step, step).tolist()
elif mc is not None:
start = float(mc.group(1))
- end = float(mc.group(2))
- num = int(mc.group(3)) if mc.group(3) is not None else 1
+ end = float(mc.group(2))
+ num = int(mc.group(3)) if mc.group(3) is not None else 1
valslist_ext += np.linspace(start=start, stop=end, num=num).tolist()
else:
@@ -545,22 +598,22 @@ class Script(scripts.Script): return valslist
x_opt = self.current_axis_options[x_type]
- if x_opt.choices is not None:
- x_values = ",".join(x_values_dropdown)
+ if x_opt.choices is not None and not csv_mode:
+ x_values = list_to_csv_string(x_values_dropdown)
xs = process_axis(x_opt, x_values, x_values_dropdown)
y_opt = self.current_axis_options[y_type]
- if y_opt.choices is not None:
- y_values = ",".join(y_values_dropdown)
+ if y_opt.choices is not None and not csv_mode:
+ y_values = list_to_csv_string(y_values_dropdown)
ys = process_axis(y_opt, y_values, y_values_dropdown)
z_opt = self.current_axis_options[z_type]
- if z_opt.choices is not None:
- z_values = ",".join(z_values_dropdown)
+ if z_opt.choices is not None and not csv_mode:
+ z_values = list_to_csv_string(z_values_dropdown)
zs = process_axis(z_opt, z_values, z_values_dropdown)
# this could be moved to common code, but unlikely to be ever triggered anywhere else
- Image.MAX_IMAGE_PIXELS = None # disable check in Pillow and rely on check below to allow large custom image sizes
+ Image.MAX_IMAGE_PIXELS = None # disable check in Pillow and rely on check below to allow large custom image sizes
grid_mp = round(len(xs) * len(ys) * len(zs) * p.width * p.height / 1000000)
assert grid_mp < opts.img_max_size_mp, f'Error: Resulting grid would be too large ({grid_mp} MPixels) (max configured size is {opts.img_max_size_mp} MPixels)'
@@ -720,9 +773,11 @@ class Script(scripts.Script): # Auto-save main and sub-grids:
grid_count = z_count + 1 if z_count > 1 else 1
for g in range(grid_count):
- #TODO: See previous comment about intentional data misalignment.
+ # TODO: See previous comment about intentional data misalignment.
adj_g = g-1 if g > 0 else g
images.save_image(processed.images[g], p.outpath_grids, "xyz_grid", info=processed.infotexts[g], extension=opts.grid_format, prompt=processed.all_prompts[adj_g], seed=processed.all_seeds[adj_g], grid=True, p=processed)
+ if not include_sub_grids: # if not include_sub_grids then skip saving after the first grid
+ break
if not include_sub_grids:
# Done with sub-grids, drop all related information:
@@ -2,6 +2,14 @@ @import url('https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600&display=swap');
+
+/* temporary fix to hide gradio crop tool until it's fixed https://github.com/gradio-app/gradio/issues/3810 */
+
+div.gradio-image button[aria-label="Edit"] {
+ display: none;
+}
+
+
/* general gradio fixes */
:root, .dark{
@@ -75,8 +83,10 @@ div.compact{ white-space: nowrap;
}
-.gradio-dropdown ul.options li.item {
- padding: 0.05em 0;
+@media (pointer:fine) {
+ .gradio-dropdown ul.options li.item {
+ padding: 0.05em 0;
+ }
}
.gradio-dropdown ul.options li.item.selected {
@@ -137,11 +147,16 @@ a{ cursor: pointer;
}
-/* gradio 3.39 puts a lot of overflow: hidden all over the place for an unknown reqasaon. */
-.block.gradio-textbox, div.gradio-group, div.gradio-group div, div.gradio-dropdown{
+/* gradio 3.39 puts a lot of overflow: hidden all over the place for an unknown reason. */
+div.gradio-container, .block.gradio-textbox, div.gradio-group, div.gradio-dropdown{
overflow: visible !important;
}
+/* align-items isn't enough and elements may overflow in Safari. */
+.unequal-height {
+ align-content: flex-start;
+}
+
/* general styled components */
@@ -166,16 +181,6 @@ a{ color: var(--button-secondary-text-color-hover);
}
-.checkboxes-row{
- margin-bottom: 0.5em;
- margin-left: 0em;
-}
-.checkboxes-row > div{
- flex: 0;
- white-space: nowrap;
- min-width: auto !important;
-}
-
button.custom-button{
border-radius: var(--button-large-radius);
padding: var(--button-large-padding);
@@ -192,13 +197,18 @@ button.custom-button{ text-align: center;
}
-div.gradio-accordion {
+div.block.gradio-accordion {
border: 1px solid var(--block-border-color) !important;
border-radius: 8px !important;
margin: 2px 0;
padding: 8px 8px;
}
+input[type="checkbox"].input-accordion-checkbox{
+ vertical-align: sub;
+ margin-right: 0.5em;
+}
+
/* txt2img/img2img specific */
@@ -239,10 +249,14 @@ div.gradio-accordion { }
[id$=_subseed_show] label{
- margin-bottom: 0.5em;
+ margin-bottom: 0.65em;
align-self: end;
}
+[id$=_seed_extras] > div{
+ gap: 0.5em;
+}
+
.html-log .comments{
padding-top: 0.5em;
}
@@ -282,14 +296,21 @@ div.gradio-accordion { min-height: 4.5em;
}
+#txt2img_generate, #img2img_generate {
+ min-height: 4.5em;
+}
+.generate-box-compact #txt2img_generate, .generate-box-compact #img2img_generate {
+ min-height: 3em;
+}
+
@media screen and (min-width: 2500px) {
#txt2img_gallery, #img2img_gallery {
min-height: 768px;
}
}
-#txt2img_gallery img, #img2img_gallery img, #extras_gallery img{
- object-fit: scale-down;
+.gradio-gallery .thumbnails img {
+ object-fit: scale-down !important;
}
#txt2img_actions_column, #img2img_actions_column {
gap: 0.5em;
@@ -352,7 +373,7 @@ div.gradio-accordion { }
div.dimensions-tools{
- min-width: 0 !important;
+ min-width: 1.6em !important;
max-width: fit-content;
flex-direction: column;
place-content: center;
@@ -369,8 +390,8 @@ div#extras_scale_to_tab div.form{ z-index: 5;
}
-.image-buttons button{
- min-width: auto;
+.image-buttons > .form{
+ justify-content: center;
}
.infotext {
@@ -389,21 +410,32 @@ div#extras_scale_to_tab div.form{ min-width: 0.5em;
}
+div.toprow-compact-stylerow{
+ margin: 0.5em 0;
+}
+
+div.toprow-compact-tools{
+ min-width: fit-content !important;
+ max-width: fit-content;
+}
+
/* settings */
#quicksettings {
- width: fit-content;
align-items: end;
}
#quicksettings > div, #quicksettings > fieldset{
- max-width: 24em;
- min-width: 24em;
- width: 24em;
+ max-width: 36em;
+ width: fit-content;
+ flex: 0 1 fit-content;
padding: 0;
border: none;
box-shadow: none;
background: none;
}
+#quicksettings > div.gradio-dropdown{
+ min-width: 24em !important;
+}
#settings{
display: block;
@@ -412,6 +444,7 @@ div#extras_scale_to_tab div.form{ #settings > div{
border: none;
margin-left: 10em;
+ padding: 0 var(--spacing-xl);
}
#settings > div.tab-nav{
@@ -426,6 +459,7 @@ div#extras_scale_to_tab div.form{ border: none;
text-align: left;
white-space: initial;
+ padding: 4px;
}
#settings_result{
@@ -503,11 +537,21 @@ table.popup-table .link{ /* live preview */
.progressDiv{
- position: relative;
+ position: absolute;
height: 20px;
background: #b4c0cc;
border-radius: 3px !important;
- margin-bottom: -3px;
+ top: -14px;
+ left: 0px;
+ width: 100%;
+}
+
+.progress-container{
+ position: relative;
+}
+
+[id$=_results].mobile{
+ margin-top: 28px;
}
.dark .progressDiv{
@@ -532,19 +576,16 @@ table.popup-table .link{ .livePreview{
position: absolute;
z-index: 300;
- background-color: white;
- margin: -4px;
-}
-
-.dark .livePreview{
- background-color: rgb(17 24 39 / var(--tw-bg-opacity));
+ background: var(--background-fill-primary);
+ width: 100%;
+ height: 100%;
}
.livePreview img{
position: absolute;
object-fit: contain;
width: 100%;
- height: 100%;
+ height: calc(100% - 60px); /* to match gradio's height */
}
/* fullscreen popup (ie in Lora's (i) button) */
@@ -566,7 +607,6 @@ table.popup-table .link{ width: 100%;
height: 100%;
overflow: auto;
- background-color: rgba(20, 20, 20, 0.95);
}
.global-popup *{
@@ -575,9 +615,6 @@ table.popup-table .link{ .global-popup-close:before {
content: "×";
-}
-
-.global-popup-close{
position: fixed;
right: 0.25em;
top: 0;
@@ -586,10 +623,20 @@ table.popup-table .link{ font-size: 32pt;
}
+.global-popup-close{
+ position: fixed;
+ left: 0;
+ top: 0;
+ width: 100%;
+ height: 100%;
+ background-color: rgba(20, 20, 20, 0.95);
+}
+
.global-popup-inner{
display: inline-block;
margin: auto;
padding: 2em;
+ z-index: 1001;
}
/* fullpage image viewer */
@@ -611,15 +658,24 @@ table.popup-table .link{ .modalControls {
display: flex;
+ position: absolute;
+ right: 0px;
+ left: 0px;
gap: 1em;
padding: 1em;
- background-color: rgba(0,0,0,0.2);
+ background-color:rgba(0,0,0,0);
+ z-index: 1;
+ transition: 0.2s ease background-color;
+}
+.modalControls:hover {
+ background-color:rgba(0,0,0,0.9);
}
.modalClose {
margin-left: auto;
}
.modalControls span{
color: white;
+ text-shadow: 0px 0px 0.25em black;
font-size: 35px;
font-weight: bold;
cursor: pointer;
@@ -784,6 +840,10 @@ footer { /* extra networks UI */
+.extra-page .prompt{
+ margin: 0 0 0.5em 0;
+}
+
.extra-network-cards{
height: calc(100vh - 24rem);
overflow: clip scroll;
@@ -848,6 +908,7 @@ footer { position: absolute;
color: white;
right: 0;
+ z-index: 1
}
.extra-network-cards .card:hover .button-row{
display: flex;
@@ -985,6 +1046,8 @@ div.block.gradio-box.edit-user-metadata { .edit-user-metadata .file-metadata th, .edit-user-metadata .file-metadata td{
padding: 0.3em 1em;
+ overflow-wrap: anywhere;
+ word-break: break-word;
}
.edit-user-metadata .wrap.translucent{
@@ -1012,10 +1075,66 @@ div.block.gradio-box.popup-dialog > div:last-child, .popup-dialog > div:last-chi }
div.block.input-accordion{
- margin-bottom: 0.4em;
+
}
.input-accordion-extra{
flex: 0 0 auto !important;
margin: 0 0.5em 0 auto;
}
+
+div.accordions > div.input-accordion{
+ min-width: fit-content !important;
+}
+
+div.accordions > div.gradio-accordion .label-wrap span{
+ white-space: nowrap;
+ margin-right: 0.25em;
+}
+
+div.accordions{
+ gap: 0.5em;
+}
+
+div.accordions > div.input-accordion.input-accordion-open{
+ flex: 1 auto;
+ flex-flow: column;
+}
+
+
+/* sticky right hand columns */
+
+#img2img_results, #txt2img_results, #extras_results {
+ position: sticky;
+ top: 0.5em;
+}
+
+body.resizing {
+ cursor: col-resize !important;
+}
+
+body.resizing * {
+ pointer-events: none !important;
+}
+
+body.resizing .resize-handle {
+ pointer-events: initial !important;
+}
+
+.resize-handle {
+ position: relative;
+ cursor: col-resize;
+ grid-column: 2 / 3;
+ min-width: 16px !important;
+ max-width: 16px !important;
+ height: 100%;
+}
+
+.resize-handle::after {
+ content: '';
+ position: absolute;
+ top: 0;
+ bottom: 0;
+ left: 7.5px;
+ border-left: 1px dashed var(--border-color-primary);
+}
diff --git a/webui-macos-env.sh b/webui-macos-env.sh index 6354e73b..24bc5c42 100644 --- a/webui-macos-env.sh +++ b/webui-macos-env.sh @@ -12,8 +12,6 @@ fi export install_dir="$HOME" export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate" export TORCH_COMMAND="pip install torch==2.0.1 torchvision==0.15.2" -export K_DIFFUSION_REPO="https://github.com/brkirch/k-diffusion.git" -export K_DIFFUSION_COMMIT_HASH="51c9778f269cedb55a4d88c79c0246d35bdadb71" export PYTORCH_ENABLE_MPS_FALLBACK=1 #################################################################### @@ -1,6 +1,11 @@ @echo off
+if exist webui.settings.bat (
+ call webui.settings.bat
+)
+
if not defined PYTHON (set PYTHON=python)
+if defined GIT (set "GIT_PYTHON_GIT_EXECUTABLE=%GIT%")
if not defined VENV_DIR (set "VENV_DIR=%~dp0%venv")
set SD_WEBUI_RESTART=tmp/restart
@@ -74,7 +74,7 @@ def webui(): if shared.opts.auto_launch_browser == "Remote" or cmd_opts.autolaunch:
auto_launch_browser = True
elif shared.opts.auto_launch_browser == "Local":
- auto_launch_browser = not any([cmd_opts.listen, cmd_opts.share, cmd_opts.ngrok])
+ auto_launch_browser = not cmd_opts.webui_is_non_local
app, local_url, share_url = shared.demo.launch(
share=cmd_opts.share,
@@ -4,12 +4,6 @@ # change the variables in webui-user.sh instead # ################################################# - -use_venv=1 -if [[ $venv_dir == "-" ]]; then - use_venv=0 -fi - SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd ) @@ -28,6 +22,12 @@ then source "$SCRIPT_DIR"/webui-user.sh fi +# If $venv_dir is "-", then disable venv support +use_venv=1 +if [[ $venv_dir == "-" ]]; then + use_venv=0 +fi + # Set defaults # Install directory without trailing slash if [[ -z "${install_dir}" ]] @@ -51,6 +51,8 @@ fi if [[ -z "${GIT}" ]] then export GIT="git" +else + export GIT_PYTHON_GIT_EXECUTABLE="${GIT}" fi # python3 venv without trailing slash (defaults to ${install_dir}/${clone_dir}/venv) @@ -141,8 +143,8 @@ case "$gpu_info" in *"Navi 2"*) export HSA_OVERRIDE_GFX_VERSION=10.3.0 ;; *"Navi 3"*) [[ -z "${TORCH_COMMAND}" ]] && \ - export TORCH_COMMAND="pip install --pre torch==2.1.0.dev-20230614+rocm5.5 torchvision==0.16.0.dev-20230614+rocm5.5 --index-url https://download.pytorch.org/whl/nightly/rocm5.5" - # Navi 3 needs at least 5.5 which is only on the nightly chain + export TORCH_COMMAND="pip install torch torchvision --index-url https://download.pytorch.org/whl/test/rocm5.6" + # Navi 3 needs at least 5.5 which is only on the torch 2.1.0 release candidates right now ;; *"Renoir"*) export HSA_OVERRIDE_GFX_VERSION=9.0.0 printf "\n%s\n" "${delimiter}" @@ -245,7 +247,7 @@ while [[ "$KEEP_GOING" -eq "1" ]]; do printf "Launching launch.py..." printf "\n%s\n" "${delimiter}" prepare_tcmalloc - "${python_cmd}" "${LAUNCH_SCRIPT}" "$@" + "${python_cmd}" -u "${LAUNCH_SCRIPT}" "$@" fi if [[ ! -f tmp/restart ]]; then |