| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2022-11-27 | Merge pull request #4663 from xucj98/draft | AUTOMATIC1111 | |
| fix the model name error of Real-ESRGAN in the opts default value | |||
| 2022-11-27 | Merge pull request #4986 from mcmonkey4eva/add-model-name | AUTOMATIC1111 | |
| add model_name pattern for saving | |||
| 2022-11-27 | Merge pull request #5085 from MrCheeze/sd-2.0-automatic-2 | AUTOMATIC1111 | |
| no-half support for SD 2.0 | |||
| 2022-11-27 | Merge pull request #4899 from liamkerr/fix_gallery_index | AUTOMATIC1111 | |
| Fixed issue with selected_gallery_index() | |||
| 2022-11-27 | Merge pull request #5065 from JaySmithWpg/vram-leak | AUTOMATIC1111 | |
| #3449 - VRAM leak when switching to/from inpainting checkpoint | |||
| 2022-11-27 | Merge pull request #4461 from brkirch/face-restoration-device-fix | AUTOMATIC1111 | |
| Fix setting device for GFPGAN and CodeFormer | |||
| 2022-11-27 | Merge pull request #4918 from brkirch/pytorch-fixes | AUTOMATIC1111 | |
| Fixes for PyTorch 1.12.1 when using MPS | |||
| 2022-11-27 | calculate dictionary for sampler names only once | AUTOMATIC | |
| 2022-11-27 | fix for broken sampler selection in img2img and xy plot #4860 #4909 | AUTOMATIC | |
| 2022-11-27 | eliminate duplicated code from #5095 | AUTOMATIC | |
| 2022-11-27 | Merge pull request #5095 from mlmcgoogan/master | AUTOMATIC1111 | |
| torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly … | |||
| 2022-11-27 | Merge pull request #4961 from uservar/DPM++SDE | AUTOMATIC1111 | |
| Add DPM++ SDE sampler | |||
| 2022-11-27 | Merge branch 'master' into DPM++SDE | AUTOMATIC1111 | |
| 2022-11-27 | Merge remote-tracking branch 'flamelaw/master' | AUTOMATIC | |
| 2022-11-27 | serve images from where they are saved instead of a temporary directory | AUTOMATIC | |
| add an option to choose a different temporary directory in the UI add an option to cleanup the selected temporary directory at startup | |||
| 2022-11-27 | Merge branch 'master' into support_any_resolution | Billy Cao | |
| 2022-11-26 | torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly set ↵ | Matthew McGoogan | |
| otherwise first. Updating torch_gc() to use the device set by --device-id if specified to avoid OOM edge cases on multi-GPU systems. | |||
| 2022-11-26 | no-half support for SD 2.0 | MrCheeze | |
| 2022-11-26 | make SD2 compatible with --medvram setting | AUTOMATIC | |
| 2022-11-27 | set TI AdamW default weight decay to 0 | flamelaw | |
| 2022-11-26 | restore hypernetworks to seemingly working state | AUTOMATIC | |
| 2022-11-26 | add 1024 module for hypernets for the new open clip | AUTOMATIC | |
| 2022-11-26 | Add support Stable Diffusion 2.0 | AUTOMATIC | |
| 2022-11-25 | fixes #3449 - VRAM leak when switching to/from inpainting model | Jay Smith | |
| 2022-11-25 | Merge branch 'AUTOMATIC1111:master' into draft | xucj98 | |
| 2022-11-24 | [interrogator] mkdir check | Tiago F. Santos | |
| 2022-11-24 | Fix other apis | Sena | |
| 2022-11-24 | Support NAI exif for PNG Info | Nandaka | |
| 2022-11-23 | add filename santization | Alex "mcmonkey" Goodwin | |
| Probably redundant, considering the model name *is* a filename, but I suppose better safe than sorry. | |||
| 2022-11-23 | add model_name pattern for saving | Alex "mcmonkey" Goodwin | |
| 2022-11-23 | last_layer_dropout default to False | flamelaw | |
| 2022-11-23 | fix dropout, implement train/eval mode | flamelaw | |
| 2022-11-23 | Patch UNet Forward to support resolutions that are not multiples of 64 | Billy Cao | |
| Also modifed the UI to no longer step in 64 | |||
| 2022-11-23 | Fix bare base64 not accept | Sena | |
| 2022-11-23 | small fixes | flamelaw | |
| 2022-11-22 | safetensors optional for now | Tim Patton | |
| 2022-11-22 | Update launch.py | uservar | |
| 2022-11-22 | Update requirements_versions.txt | uservar | |
| 2022-11-22 | Update requirements.txt | uservar | |
| 2022-11-22 | Add DPM++ SDE sampler | uservar | |
| 2022-11-22 | Update k-diffusion to Release 0.0.11 | uservar | |
| 2022-11-22 | fix null negative_prompt on get requests | Rogerooo | |
| Small typo that causes a bug when returning negative prompts from the get request. | |||
| 2022-11-22 | [CLIP interrogator] use local file, if available | Tiago F. Santos | |
| 2022-11-21 | Use GPU for loading safetensors, disable export | Tim Patton | |
| 2022-11-21 | Ignore safetensor files | Tim Patton | |
| 2022-11-21 | Patch line ui endings | Tim Patton | |
| 2022-11-21 | Supporting `*.safetensors` format. | Nicolas Patry | |
| If a model file exists with extension `.safetensors` then we can load it more safely than with PyTorch weights. | |||
| 2022-11-21 | Change .cuda() to .to(devices.device) | brkirch | |
| 2022-11-21 | Add fixes for PyTorch 1.12.1 | brkirch | |
| Fix typo "MasOS" -> "macOS" If MPS is available and PyTorch is an earlier version than 1.13: * Monkey patch torch.Tensor.to to ensure all tensors sent to MPS are contiguous * Monkey patch torch.nn.functional.layer_norm to ensure input tensor is contiguous (required for this program to work with MPS on unmodified PyTorch 1.12.1) | |||
| 2022-11-21 | remove cmd args requirement for deepdanbooru | dtlnor | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |