Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Merge pull request #4986 from mcmonkey4eva/add-model-name | AUTOMATIC1111 | 2022-11-27 | 2 | -2/+3 |
|\ | | | | | add model_name pattern for saving | ||||
| * | add filename santization | Alex "mcmonkey" Goodwin | 2022-11-23 | 1 | -1/+1 |
| | | | | | | | | Probably redundant, considering the model name *is* a filename, but I suppose better safe than sorry. | ||||
| * | add model_name pattern for saving | Alex "mcmonkey" Goodwin | 2022-11-23 | 2 | -2/+3 |
| | | |||||
* | | Merge pull request #5085 from MrCheeze/sd-2.0-automatic-2 | AUTOMATIC1111 | 2022-11-27 | 1 | -0/+3 |
|\ \ | | | | | | | no-half support for SD 2.0 | ||||
| * | | no-half support for SD 2.0 | MrCheeze | 2022-11-26 | 1 | -0/+3 |
| | | | |||||
* | | | Merge pull request #4899 from liamkerr/fix_gallery_index | AUTOMATIC1111 | 2022-11-27 | 1 | -2/+2 |
|\ \ \ | | | | | | | | | Fixed issue with selected_gallery_index() | ||||
| * | | | made selected_gallery_index query selectors more restrictive | Liam | 2022-11-20 | 1 | -2/+2 |
| | | | | |||||
* | | | | Merge pull request #5065 from JaySmithWpg/vram-leak | AUTOMATIC1111 | 2022-11-27 | 1 | -18/+15 |
|\ \ \ \ | | | | | | | | | | | #3449 - VRAM leak when switching to/from inpainting checkpoint | ||||
| * | | | | fixes #3449 - VRAM leak when switching to/from inpainting model | Jay Smith | 2022-11-26 | 1 | -18/+15 |
| | |_|/ | |/| | | |||||
* | | | | Merge pull request #4461 from brkirch/face-restoration-device-fix | AUTOMATIC1111 | 2022-11-27 | 2 | -1/+6 |
|\ \ \ \ | | | | | | | | | | | Fix setting device for GFPGAN and CodeFormer | ||||
| * | | | | Set device for facelib/facexlib and gfpgan | brkirch | 2022-11-12 | 2 | -1/+6 |
| | | | | | | | | | | | | | | | | | | | | | | | | | * FaceXLib/FaceLib doesn't pass the device argument to RetinaFace but instead chooses one itself and sets it to a global - in order to use a device other than its internally chosen default it is necessary to manually replace the default value * The GFPGAN constructor needs the device argument to work with MPS or a CUDA device ID that differs from the default | ||||
* | | | | | Merge pull request #4918 from brkirch/pytorch-fixes | AUTOMATIC1111 | 2022-11-27 | 4 | -10/+27 |
|\ \ \ \ \ | | | | | | | | | | | | | Fixes for PyTorch 1.12.1 when using MPS | ||||
| * | | | | | Add fixes for PyTorch 1.12.1 | brkirch | 2022-11-21 | 1 | -1/+27 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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) | ||||
| * | | | | | Remove extra .to(device) | brkirch | 2022-11-17 | 1 | -1/+0 |
| | | | | | | |||||
| * | | | | | Revert "MPS Upscalers Fix" | brkirch | 2022-11-17 | 4 | -12/+4 |
| | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 768b95394a8500da639b947508f78296524f1836. | ||||
* | | | | | | calculate dictionary for sampler names only once | AUTOMATIC | 2022-11-27 | 2 | -12/+9 |
| | | | | | | |||||
* | | | | | | fix for broken sampler selection in img2img and xy plot #4860 #4909 | AUTOMATIC | 2022-11-27 | 3 | -9/+9 |
| | | | | | | |||||
* | | | | | | eliminate duplicated code from #5095 | AUTOMATIC | 2022-11-27 | 1 | -19/+11 |
| | | | | | | |||||
* | | | | | | Merge pull request #5095 from mlmcgoogan/master | AUTOMATIC1111 | 2022-11-27 | 1 | -2/+12 |
|\ \ \ \ \ \ | | | | | | | | | | | | | | | torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly … | ||||
| * | | | | | | torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly set ↵ | Matthew McGoogan | 2022-11-26 | 1 | -2/+12 |
| | |_|_|_|/ | |/| | | | | | | | | | | | | | | | | otherwise first. Updating torch_gc() to use the device set by --device-id if specified to avoid OOM edge cases on multi-GPU systems. | ||||
* | | | | | | Merge pull request #4961 from uservar/DPM++SDE | AUTOMATIC1111 | 2022-11-27 | 1 | -0/+2 |
|\ \ \ \ \ \ | | | | | | | | | | | | | | | Add DPM++ SDE sampler | ||||
| * \ \ \ \ \ | Merge branch 'master' into DPM++SDE | AUTOMATIC1111 | 2022-11-27 | 19 | -671/+1063 |
| |\ \ \ \ \ \ | |/ / / / / / |/| | | | | | | |||||
* | | | | | | | Merge remote-tracking branch 'flamelaw/master' | AUTOMATIC | 2022-11-27 | 7 | -322/+473 |
|\ \ \ \ \ \ \ | |||||
| * | | | | | | | set TI AdamW default weight decay to 0 | flamelaw | 2022-11-26 | 1 | -1/+1 |
| | | | | | | | | |||||
| * | | | | | | | last_layer_dropout default to False | flamelaw | 2022-11-23 | 1 | -1/+1 |
| | | | | | | | | |||||
| * | | | | | | | fix dropout, implement train/eval mode | flamelaw | 2022-11-23 | 1 | -6/+18 |
| | | | | | | | | |||||
| * | | | | | | | small fixes | flamelaw | 2022-11-22 | 2 | -4/+4 |
| | | | | | | | | |||||
| * | | | | | | | fix pin_memory with different latent sampling method | flamelaw | 2022-11-21 | 3 | -11/+24 |
| | | | | | | | | |||||
| * | | | | | | | fix random sampling with pin_memory | flamelaw | 2022-11-20 | 1 | -1/+1 |
| | | | | | | | | |||||
| * | | | | | | | remove unnecessary comment | flamelaw | 2022-11-20 | 1 | -9/+0 |
| | | | | | | | | |||||
| * | | | | | | | Gradient accumulation, autocast fix, new latent sampling method, etc | flamelaw | 2022-11-20 | 7 | -313/+448 |
| | | | | | | | | |||||
* | | | | | | | | serve images from where they are saved instead of a temporary directory | AUTOMATIC | 2022-11-27 | 5 | -21/+82 |
| |_|/ / / / / |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | add an option to choose a different temporary directory in the UI add an option to cleanup the selected temporary directory at startup | ||||
* | | | | | | | make SD2 compatible with --medvram setting | AUTOMATIC | 2022-11-26 | 1 | -0/+8 |
| | | | | | | | |||||
* | | | | | | | restore hypernetworks to seemingly working state | AUTOMATIC | 2022-11-26 | 2 | -2/+3 |
| | | | | | | | |||||
* | | | | | | | add 1024 module for hypernets for the new open clip | AUTOMATIC | 2022-11-26 | 1 | -1/+1 |
| | | | | | | | |||||
* | | | | | | | Add support Stable Diffusion 2.0 | AUTOMATIC | 2022-11-26 | 15 | -331/+504 |
| |_|_|_|/ / |/| | | | | | |||||
| | * | | | | Update launch.py | uservar | 2022-11-22 | 1 | -1/+1 |
| | | | | | | |||||
| | * | | | | Update requirements_versions.txt | uservar | 2022-11-22 | 1 | -0/+1 |
| | | | | | | |||||
| | * | | | | Update requirements.txt | uservar | 2022-11-22 | 1 | -0/+1 |
| | | | | | | |||||
| | * | | | | Add DPM++ SDE sampler | uservar | 2022-11-22 | 1 | -0/+2 |
| | | | | | | |||||
| | * | | | | Update k-diffusion to Release 0.0.11 | uservar | 2022-11-22 | 1 | -1/+1 |
| |/ / / / |/| | | | | |||||
* | | | | | Merge pull request #4120 from aliencaocao/enable-override-hypernet | AUTOMATIC1111 | 2022-11-20 | 1 | -2/+4 |
|\ \ \ \ \ | |_|_|_|/ |/| | | | | Enable override_settings to take effect for hypernetworks | ||||
| * | | | | Merge branch 'master' into enable-override-hypernet | Billy Cao | 2022-11-06 | 50 | -723/+2527 |
| |\ \ \ \ | |||||
| * | | | | | Resolve conflict | Billy Cao | 2022-11-06 | 1 | -2/+2 |
| | | | | | | |||||
| * | | | | | Merge branch 'AUTOMATIC1111:master' into enable-override-hypernet | Billy Cao | 2022-11-01 | 3 | -1/+29 |
| |\ \ \ \ \ | |||||
| * | | | | | | Enable override_settings to take effect for hypernetworks | Billy Cao | 2022-11-01 | 1 | -2/+4 |
| | | | | | | | |||||
* | | | | | | | moved deepdanbooru to pure pytorch implementation | AUTOMATIC | 2022-11-20 | 8 | -195/+777 |
| |_|_|/ / / |/| | | | | | |||||
* | | | | | | revert change to webui-user.bat | AUTOMATIC | 2022-11-19 | 1 | -1/+0 |
| | | | | | | |||||
* | | | | | | Add API for scripts to add elements anywhere in UI. | AUTOMATIC | 2022-11-19 | 3 | -5/+111 |
| | | | | | | |||||
* | | | | | | Merge pull request #4717 from papuSpartan/security | AUTOMATIC1111 | 2022-11-19 | 2 | -2/+5 |
|\ \ \ \ \ \ | | | | | | | | | | | | | | | Add --server-name to the list of arguments considered insecure |