| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2022-12-08 | Add latent upscale option to img2img | Andrew Ryan | -2/+6 | |
| 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 | ||||
| 2022-12-04 | make it possible to merge inpainting model with non-inpainting one | AUTOMATIC | -2/+25 | |
| 2022-12-04 | fix #4459 breaking inpainting when the option is not specified. | AUTOMATIC | -19/+23 | |
| 2022-12-03 | fix incorrect file extension filter for deepdanbooru models | AUTOMATIC | -1/+1 | |
| 2022-12-03 | use modelloader for #4956 | AUTOMATIC | -14/+8 | |
| 2022-12-03 | Merge pull request #4956 from TiagoSantos81/offline_BLIP | AUTOMATIC1111 | -1/+12 | |
| [CLIP interrogator] use local file, if available | ||||
| 2022-12-03 | move #5216 to the extension | AUTOMATIC | -287/+1 | |
| 2022-12-03 | Merge remote-tracking branch 'wywywywy/autoencoder-hijack' | AUTOMATIC | -1/+287 | |
| 2022-12-03 | add built-in extension system | AUTOMATIC | -2710/+42 | |
| add support for adding upscalers in extensions move LDSR, ScuNET and SwinIR to built-in extensions | ||||
| 2022-12-03 | add comment for #4407 and remove seemingly unnecessary cudnn.enabled | AUTOMATIC | -1/+3 | |
| 2022-12-03 | fix #4407 breaking UI entirely for card other than ones related to the PR | AUTOMATIC | -4/+2 | |
| 2022-12-03 | Merge pull request #4407 from yoinked-h/patch-1 | AUTOMATIC1111 | -0/+7 | |
| Fix issue with 16xx cards | ||||
| 2022-12-03 | Merge pull request #5251 from adieyal/bug/negative-prompt-infotext | AUTOMATIC1111 | -1/+1 | |
| Fixed incorrect negative prompt text in infotext | ||||
| 2022-12-03 | Merge branch 'master' into racecond_fix | AUTOMATIC1111 | -1375/+3161 | |
| 2022-12-03 | Merge pull request #4459 from kavorite/color-sketch-inpainting | AUTOMATIC1111 | -10/+36 | |
| add `--gradio-inpaint-tool` and option to specify `color-sketch` | ||||
| 2022-12-03 | Merge pull request #5194 from brkirch/autocast-and-mps-randn-fixes | AUTOMATIC1111 | -31/+29 | |
| Use devices.autocast() and fix MPS randn issues | ||||
| 2022-12-03 | more simple config option name plus mouseover hint for clip skip | AUTOMATIC | -1/+1 | |
| 2022-12-03 | Merge pull request #5304 from space-nuko/fix/clip-skip-application | AUTOMATIC1111 | -1/+5 | |
| Fix clip skip of 1 not being restored from prompts | ||||
| 2022-12-03 | Merge pull request #5328 from jcowens/fix-typo | AUTOMATIC1111 | -1/+1 | |
| fix typo | ||||
| 2022-12-03 | Merge pull request #5331 from smirkingface/openaimodel_fix | AUTOMATIC1111 | -0/+1 | |
| Fixed AttributeError where openaimodel is not found | ||||
| 2022-12-03 | Merge pull request #5340 from PhytoEpidemic/master | AUTOMATIC1111 | -3/+3 | |
| Fix divide by 0 error | ||||
| 2022-12-03 | prevent include_init_images from being passed to ↵ | AUTOMATIC | -2/+5 | |
| StableDiffusionProcessingImg2Img in API #4989 | ||||
| 2022-12-03 | Merge pull request #5165 from klimaleksus/fix-sequential-vae | AUTOMATIC1111 | -2/+2 | |
| Make VAE step sequential to prevent VRAM spikes, will fix #3059, #2082, #2561, #3462 | ||||
| 2022-12-02 | Fix divide by 0 error | PhytoEpidemic | -3/+3 | |
| Fix of the edge case 0 weight that occasionally will pop up in some specific situations. This was crashing the script. | ||||
| 2022-12-02 | Fixed AttributeError where openaimodel is not found | SmirkingFace | -0/+1 | |
| 2022-12-02 | fix typo | jcowens | -1/+1 | |
| 2022-12-02 | Fixed safe.py for pytorch 1.13 ckpt files | SmirkingFace | -7/+11 | |
| 2022-12-01 | Fix clip skip of 1 not being restored from prompts | space-nuko | -1/+5 | |
| 2022-11-30 | Rework MPS randn fix, add randn_like fix | brkirch | -15/+8 | |
| torch.manual_seed() already sets a CPU generator, so there is no reason to create a CPU generator manually. torch.randn_like also needs a MPS fix for k-diffusion, but a torch hijack with randn_like already exists so it can also be used for that. | ||||
| 2022-11-30 | Use devices.autocast instead of torch.autocast | brkirch | -11/+6 | |
| 2022-11-30 | Add workaround for using MPS with torchsde | brkirch | -0/+14 | |
| 2022-11-30 | Fixed incorrect negative prompt text in infotext | Adi Eyal | -1/+1 | |
| Previously only the first negative prompt in all_negative_prompts was being used for infotext. This fixes that by selecting the index-th negative prompt | ||||
| 2022-11-29 | Added purpose of this hijack to comments | wywywywy | -0/+4 | |
| 2022-11-29 | Add autoencoder to sd_hijack | wywywywy | -1/+1 | |
| 2022-11-29 | Hijack VQModelInterface back to AutoEncoder | wywywywy | -0/+282 | |
| 2022-11-29 | Merge remote-tracking branch 'pattontim/safetensors' | AUTOMATIC | -0/+1 | |
| 2022-11-28 | Refactor and instead check if mps is being used, not availability | brkirch | -5/+1 | |
| 2022-11-28 | Make VAE step sequential to prevent VRAM spikes | klimaleksus | -2/+2 | |
| 2022-11-28 | fix an error that happens when you type into prompt while switching model, ↵ | AUTOMATIC | -64/+101 | |
| put queue stuff into separate file | ||||
| 2022-11-28 | make it possible to save nai model using safetensors | AUTOMATIC | -2/+2 | |
| 2022-11-27 | if image on disk was deleted between being generated and request being ↵ | AUTOMATIC | -1/+1 | |
| completed, do use temporary dir to store it for the browser | ||||
| 2022-11-27 | fix the bug that makes it impossible to send images to other tabs | AUTOMATIC | -3/+4 | |
| 2022-11-27 | Merge pull request #4688 from parasi22/resolve-embedding-name-in-filewords | AUTOMATIC1111 | -1/+1 | |
| resolve [name] after resolving [filewords] in training | ||||
| 2022-11-27 | Merge pull request #4416 from Keavon/cors-regex | AUTOMATIC1111 | -4/+5 | |
| Add CORS-allow policy launch argument using regex | ||||
| 2022-11-27 | Merge pull request #4919 from brkirch/deepbooru-fix | AUTOMATIC1111 | -1/+1 | |
| Fix support for devices other than CUDA in DeepBooru | ||||
| 2022-11-27 | Merge pull request #5117 from aliencaocao/fix_api_sampler_name | AUTOMATIC1111 | -2/+6 | |
| Fix api ignoring sampler_name settings | ||||
| 2022-11-27 | Merge pull request #4960 from Hugo-Matias/master | AUTOMATIC1111 | -1/+1 | |
| fix null negative_prompt on get requests | ||||
| 2022-11-27 | cherrypick from #4971 | AUTOMATIC | -0/+1 | |
| 2022-11-27 | Merge pull request #4583 from NoCrypt/patch-1 | AUTOMATIC1111 | -2/+2 | |
| Forcing HTTPS instead of HTTP for ngrok | ||||
| 2022-11-27 | rework #5012 to also work for pictures dragged into the prompt and also add ↵ | AUTOMATIC | -37/+44 | |
| Clip skip + ENSD to parameters | ||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |