| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2023-01-27 | add v2-inpainting model detection, and broaden v-model detection to include ↵ | MrCheeze | |
| anything with 768 in the name | |||
| 2023-01-27 | fix broken calls to find_checkpoint_config | AUTOMATIC | |
| 2023-01-27 | clarify the option to disable NaN check. | AUTOMATIC | |
| 2023-01-27 | support detecting midas model | AUTOMATIC | |
| fix broken api for checkpoint list | |||
| 2023-01-27 | remove the need to place configs near models | AUTOMATIC | |
| 2023-01-26 | add an option to enable sections from extras tab in txt2img/img2img | AUTOMATIC | |
| fix some style inconsistenices | |||
| 2023-01-26 | Merge pull request #7234 from brkirch/fix-full-previews | AUTOMATIC1111 | |
| Fix full previews and--no-half-vae to work correctly with --upcast-sampling | |||
| 2023-01-26 | Fix full previews, --no-half-vae | brkirch | |
| 2023-01-25 | fix prompt editing break after first batch in img2img | AUTOMATIC | |
| 2023-01-25 | add edit_image_conditioning from my earlier edits in case there's an attempt ↵ | AUTOMATIC | |
| to inegrate pix2pix properly this allows to use pix2pix model in img2img though it won't work well this way | |||
| 2023-01-25 | Merge pull request #7197 from mcmonkey4eva/fix-ti-symlinks | AUTOMATIC1111 | |
| allow symlinks in the textual inversion embeddings folder | |||
| 2023-01-25 | Merge pull request #7201 from brkirch/update-macos-defaults | AUTOMATIC1111 | |
| Update default Mac command line arguments to use --upcast-sampling instead of --no-half | |||
| 2023-01-25 | Update arguments to use --upcast-sampling | brkirch | |
| 2023-01-25 | fix for unet hijack breaking the train tab | AUTOMATIC | |
| 2023-01-25 | make clicking extra networks button one more time close the extra networks UI | AUTOMATIC | |
| 2023-01-25 | allow symlinks in the textual inversion embeddings folder | Alex "mcmonkey" Goodwin | |
| 2023-01-25 | add pix2pix credits | AUTOMATIC | |
| 2023-01-25 | Merge pull request #6510 from brkirch/unet16-upcast-precision | AUTOMATIC1111 | |
| Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half | |||
| 2023-01-25 | Merge pull request #7138 from mykeehu/patch-4 | AUTOMATIC1111 | |
| Fix extra network thumbs label color | |||
| 2023-01-25 | change to code for live preview fix on OSX to be bit more obvious | AUTOMATIC | |
| 2023-01-25 | Merge pull request #7151 from brkirch/fix-approx-nn | AUTOMATIC1111 | |
| Fix Approx NN previews changing first generation result | |||
| 2023-01-25 | Merge pull request #7195 from Klace/instruct-pix2pix_model_load | AUTOMATIC1111 | |
| Add instruct-pix2pix hijack | |||
| 2023-01-25 | Update requirements transformers==4.25.1 | Kyle | |
| Update requirement for transformers to version 4.25.1 to allow instruct-pix2pix demo code to work | |||
| 2023-01-25 | Add instruct-pix2pix hijack | Kyle | |
| Allows loading instruct-pix2pix models via same method as inpainting models in sd_models.py and sd_hijack_ip2p.py Adds ddpm_edit.py necessary for instruct-pix2pix | |||
| 2023-01-25 | Merge pull request #7146 from EllangoK/master | AUTOMATIC1111 | |
| Adds X/Y/Z Grid Script | |||
| 2023-01-25 | add an experimental option to apply loras to outputs rather than inputs | AUTOMATIC | |
| 2023-01-25 | Add UI setting for upcasting attention to float32 | brkirch | |
| Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers. In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also. | |||
| 2023-01-25 | Add option for float32 sampling with float16 UNet | brkirch | |
| This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half(). | |||
| 2023-01-25 | remove the pip install stuff because it does not work as i hoped it would | AUTOMATIC | |
| 2023-01-24 | add fastapi to requirements | AUTOMATIC | |
| 2023-01-24 | print progress when installing torch | AUTOMATIC | |
| add PIP_INSTALLER_LOCATION env var to install pip if it's not installed remove accidental call to accelerate when venv is disabled add another env var to skip venv - SKIP_VENV | |||
| 2023-01-24 | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵ | AUTOMATIC | |
| about it mk2 | |||
| 2023-01-24 | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵ | AUTOMATIC | |
| about it | |||
| 2023-01-24 | make git commands not fail for extensions when you have spaces in webui ↵ | AUTOMATIC | |
| directory | |||
| 2023-01-24 | swaps xyz axes internally if one costs more | EllangoK | |
| 2023-01-24 | handling sub grids and merging into one | EllangoK | |
| 2023-01-24 | implements most of xyz grid script | EllangoK | |
| 2023-01-24 | renamed xy to xyz grid | EllangoK | |
| this is mostly just so git can detect it properly | |||
| 2023-01-24 | also return the removed field to sdapi/v1/upscalers because someone might ↵ | AUTOMATIC | |
| have relied on it existing | |||
| 2023-01-24 | repair sdapi/v1/upscalers returning bogus results | AUTOMATIC | |
| 2023-01-24 | Merge pull request #7140 from vladmandic/api-decode-image | AUTOMATIC1111 | |
| Add exception handling to API image decode | |||
| 2023-01-24 | Merge pull request #7144 from catboxanon/swinir-interrupt | AUTOMATIC1111 | |
| Make SwinIR upscaler interruptible and skippable | |||
| 2023-01-24 | Merge pull request #7148 from acncagua/improvement_launch.py | AUTOMATIC1111 | |
| Set Linux xformers 0.0.16RC425 | |||
| 2023-01-23 | Fix different first gen with Approx NN previews | brkirch | |
| The loading of the model for approx nn live previews can change the internal state of PyTorch, resulting in a different image. This can be avoided by preloading the approx nn model in advance. | |||
| 2023-01-24 | Set Linux xformers 0.0.16RC425 | acncagua | |
| 2023-01-23 | Also make SwinIR skippable | catboxanon | |
| 2023-01-23 | Make SwinIR interruptible | catboxanon | |
| 2023-01-23 | add image decod exception handling | Vladimir Mandic | |
| 2023-01-23 | Fix extra network thumbs label color | Mykeehu | |
| Added white color for labels. | |||
| 2023-01-24 | fix BLIP failing to import depending on configuration | AUTOMATIC | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |