| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2022-12-17 | Update OptionInfo to match preexisting option. | timntorres | |
| 2022-12-17 | Add option to include upscaler name in filename. | timntorres | |
| 2022-12-17 | Add upscaler name as a suffix. | timntorres | |
| 2022-12-17 | Add attributes used by MPS | brkirch | |
| 2022-12-17 | Add numpy fix for MPS on PyTorch 1.12.1 | brkirch | |
| When saving training results with torch.save(), an exception is thrown: "RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead." So for MPS, check if Tensor.requires_grad and detach() if necessary. | |||
| 2022-12-17 | fix: Modify font size when unable to fit in plot | MMaker | |
| This prevents scenarios where text without line breaks will start overlapping with each other when generating X/Y plots. This is most evident when generating X/Y plots with checkpoints, as most don't contain spaces and sometimes include extra information such as the epoch, making it extra long. | |||
| 2022-12-16 | apply to DPM2 (non-ancestral) as well | Alex "mcmonkey" Goodwin | |
| 2022-12-16 | Add a workaround patch for DPM2 a issue | Alex "mcmonkey" Goodwin | |
| DPM2 a and DPM2 a Karras samplers are both affected by an issue described by https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3483 and can be resolved by a workaround suggested by the k-diffusion author at https://github.com/crowsonkb/k-diffusion/issues/43#issuecomment-1305195666 | |||
| 2022-12-16 | fix: xformers | Akiba | |
| 2022-12-14 | Fix various typos | Jim Hays | |
| 2022-12-14 | Correct singleton comparisons | Yuval Aboulafia | |
| 2022-12-13 | Fix comment | space-nuko | |
| 2022-12-13 | Correctly restore default hypernetwork strength | space-nuko | |
| 2022-12-13 | Correctly restore hypernetwork from hash | space-nuko | |
| 2022-12-13 | Save hypernetwork hash in infotext | space-nuko | |
| 2022-12-11 | Improve color correction with luminosity blend | ThereforeGames | |
| 2022-12-11 | API endpoint to refresh checkpoints | Dean Hopkins | |
| API endpoint to refresh checkpoints | |||
| 2022-12-11 | unconditionally set use_ema=False if value not specified (True never worked, ↵ | MrCheeze | |
| and all configs except v1-inpainting-inference.yaml already correctly set it to False) | |||
| 2022-12-11 | fix: fallback model_checkpoint if it's empty | Dean van Dugteren | |
| This fixes the following error when SD attempts to start with a deleted checkpoint: ``` Traceback (most recent call last): File "D:\Web\stable-diffusion-webui\launch.py", line 295, in <module> start() File "D:\Web\stable-diffusion-webui\launch.py", line 290, in start webui.webui() File "D:\Web\stable-diffusion-webui\webui.py", line 132, in webui initialize() File "D:\Web\stable-diffusion-webui\webui.py", line 62, in initialize modules.sd_models.load_model() File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 283, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 117, in select_checkpoint checkpoint_info = checkpoints_list.get(model_checkpoint, None) TypeError: unhashable type: 'list' ``` | |||
| 2022-12-10 | fix support for 2.0 inpainting model while maintaining support for 1.5 ↵ | MrCheeze | |
| inpainting model | |||
| 2022-12-10 | unload depth model if medvram/lowvram enabled | MrCheeze | |
| 2022-12-10 | Merge pull request #5191 from ↵ | AUTOMATIC1111 | |
| aliencaocao/enable_checkpoint_switching_in_override_settings Support changing checkpoint and vae through override_settings | |||
| 2022-12-10 | add an 'installed' tag to extensions | AUTOMATIC | |
| 2022-12-10 | remove NSFW filter and its dependency; if you still want it, find it in the ↵ | AUTOMATIC | |
| extensions section | |||
| 2022-12-10 | use less javascript for this non-js-only implementation of the clear prompt ↵ | AUTOMATIC | |
| button. | |||
| 2022-12-10 | Merge pull request #3198 from papuSpartan/master | AUTOMATIC1111 | |
| Add Clear Prompt button to roll_col | |||
| 2022-12-10 | Merge pull request #5119 from 0xb8/master | AUTOMATIC1111 | |
| Atomically rename saved image to avoid race condition with other processes | |||
| 2022-12-10 | Merge pull request #5441 from timntorres/add-5433-avoid-sending-size-option | AUTOMATIC1111 | |
| Add option to avoid sending size between interfaces. | |||
| 2022-12-10 | Merge branch 'AUTOMATIC1111:master' into master | papuSpartan | |
| 2022-12-10 | Merge pull request #4841 from R-N/vae-fix-none | AUTOMATIC1111 | |
| Fix None option of VAE selector | |||
| 2022-12-10 | add Noise multiplier option to infotext | AUTOMATIC | |
| 2022-12-10 | Merge pull request #5373 from mezotaken/master | AUTOMATIC1111 | |
| add noise strength parameter similar to NAI | |||
| 2022-12-10 | Merge pull request #5404 from szhublox/merger-ram-usage | AUTOMATIC1111 | |
| Merger ram usage | |||
| 2022-12-10 | cleanup some unneeded imports for hijack files | AUTOMATIC | |
| 2022-12-10 | do not replace entire unet for the resolution hack | AUTOMATIC | |
| 2022-12-10 | Merge pull request #4978 from aliencaocao/support_any_resolution | AUTOMATIC1111 | |
| Patch UNet Forward to support resolutions that are not multiples of 64 | |||
| 2022-12-10 | Merge pull request #5555 from ywx9/master | AUTOMATIC1111 | |
| Bug fix (a few lines in modules/api/api.py) | |||
| 2022-12-10 | Merge pull request #5547 from Ju1-js/master | AUTOMATIC1111 | |
| Make "# settings changed" grammatically correct | |||
| 2022-12-09 | Bug fix | ywx9 | |
| 2022-12-08 | Make # settings changed message grammatically correct | Ju1-js | |
| Make the ": " in the settings changed message not show if 0 settings were changed. "0 settings changed: ." -> "0 settings changed." | |||
| 2022-12-08 | Depth2img model support | Jay Smith | |
| 2022-12-08 | Add latent upscale option to img2img | Andrew Ryan | |
| Recently, the option to do latent upscale was added to txt2img highres fix. This feature runs by scaling the latent sample of the image, and then running a second pass of img2img. But, in this edition of highres fix, the image and parameters cannot be changed between the first pass and second pass. We might want to do a fixup in img2img before doing the second pass, or might want to run the second pass at a different resolution. This change adds the option for img2img to perform its upscale in latent space, rather than image space, giving very similar results to highres fix with latent upscale. The result is not exactly the same because there is an additional latent -> decoder -> image -> encoder -> latent that won't happen in highres fix, but this conversion has relatively small losses | |||
| 2022-12-05 | Add opt. to avoid sending size between interfaces. | timntorres | |
| 2022-12-04 | extras.py: use as little RAM as possible, misc fixes | Mackerel | |
| maximum of 2 models loaded at once. delete unneeded model before next step. fix 'teritary' -> 'tertiary'. gracefully fail when "add difference" is selected without a tertiary model | |||
| 2022-12-04 | make it possible to merge inpainting model with non-inpainting one | AUTOMATIC | |
| 2022-12-04 | fix #4459 breaking inpainting when the option is not specified. | AUTOMATIC | |
| 2022-12-03 | fix incorrect file extension filter for deepdanbooru models | AUTOMATIC | |
| 2022-12-03 | use modelloader for #4956 | AUTOMATIC | |
| 2022-12-03 | Merge pull request #4956 from TiagoSantos81/offline_BLIP | AUTOMATIC1111 | |
| [CLIP interrogator] use local file, if available | |||
| 2022-12-03 | move #5216 to the extension | AUTOMATIC | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |