| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | | clarify the option to disable NaN check. | AUTOMATIC | 2023-01-27 | 1 | -0/+2 | |
| | | | ||||||
| * | | remove the need to place configs near models | AUTOMATIC | 2023-01-27 | 1 | -4/+8 | |
| |/ | ||||||
| * | Add UI setting for upcasting attention to float32 | brkirch | 2023-01-25 | 1 | -1/+5 | |
| | | | | | | | 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. | |||||
| * | Add option for float32 sampling with float16 UNet | brkirch | 2023-01-25 | 1 | -0/+2 | |
| | | | | | 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(). | |||||
| * | Merge pull request #6922 from brkirch/cumsum-fix | AUTOMATIC1111 | 2023-01-19 | 1 | -4/+7 | |
| |\ | | | | | Improve cumsum fix for MPS | |||||
| | * | Fix cumsum for MPS in newer torch | brkirch | 2023-01-18 | 1 | -4/+7 | |
| | | | | | | | | | The prior fix assumed that testing int16 was enough to determine if a fix is needed, but a recent fix for cumsum has int16 working but not bool. | |||||
| * | | disable the new NaN check for the CI | AUTOMATIC | 2023-01-17 | 1 | -0/+3 | |
| | | | ||||||
| * | | Add a check and explanation for tensor with all NaNs. | AUTOMATIC | 2023-01-16 | 1 | -0/+28 | |
| |/ | ||||||
| * | Add support for PyTorch nightly and local builds | brkirch | 2023-01-06 | 1 | -5/+23 | |
| | | ||||||
| * | Add numpy fix for MPS on PyTorch 1.12.1 | brkirch | 2022-12-17 | 1 | -0/+9 | |
| | | | | | | | | 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. | |||||
| * | add built-in extension system | AUTOMATIC | 2022-12-03 | 1 | -1/+10 | |
| | | | | | | add support for adding upscalers in extensions move LDSR, ScuNET and SwinIR to built-in extensions | |||||
| * | add comment for #4407 and remove seemingly unnecessary cudnn.enabled | AUTOMATIC | 2022-12-03 | 1 | -1/+3 | |
| | | ||||||
| * | fix #4407 breaking UI entirely for card other than ones related to the PR | AUTOMATIC | 2022-12-03 | 1 | -4/+2 | |
| | | ||||||
| * | Merge pull request #4407 from yoinked-h/patch-1 | AUTOMATIC1111 | 2022-12-03 | 1 | -0/+7 | |
| |\ | | | | | Fix issue with 16xx cards | |||||
| | * | actual better fix | pepe10-gpu | 2022-11-08 | 1 | -5/+2 | |
| | | | | | | | thanks C43H66N12O12S2 | |||||
| | * | terrible hack | pepe10-gpu | 2022-11-08 | 1 | -2/+9 | |
| | | | ||||||
| | * | 16xx card fix | pepe10-gpu | 2022-11-07 | 1 | -0/+3 | |
| | | | | | | | cudnn | |||||
| * | | Rework MPS randn fix, add randn_like fix | brkirch | 2022-11-30 | 1 | -12/+3 | |
| | | | | | | | | | 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. | |||||
| * | | Merge pull request #4918 from brkirch/pytorch-fixes | AUTOMATIC1111 | 2022-11-27 | 1 | -7/+24 | |
| |\ \ | | | | | | | 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) | |||||
| | * | | Revert "MPS Upscalers Fix" | brkirch | 2022-11-17 | 1 | -9/+0 | |
| | | | | | | | | | | | | | This reverts commit 768b95394a8500da639b947508f78296524f1836. | |||||
| * | | | eliminate duplicated code from #5095 | AUTOMATIC | 2022-11-27 | 1 | -19/+11 | |
| | | | | ||||||
| * | | | 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. | |||||
| * | | change formatting to match the main program in devices.py | AUTOMATIC | 2022-11-12 | 1 | -5/+16 | |
| | | | ||||||
| * | | Update devices.py | 源文雨 | 2022-11-12 | 1 | -1/+1 | |
| | | | ||||||
| * | | Fix wrong mps selection below MasOS 12.3 | 源文雨 | 2022-11-12 | 1 | -3/+10 | |
| |/ | ||||||
| * | MPS Upscalers Fix | brkirch | 2022-10-25 | 1 | -0/+4 | |
| | | | | | Get ESRGAN, SCUNet, and SwinIR working correctly on MPS by ensuring memory is contiguous for tensor views before sending to MPS device. | |||||
| * | Remove BSRGAN from --use-cpu, add SwinIR | brkirch | 2022-10-25 | 1 | -1/+1 | |
| | | ||||||
| * | remove parsing command line from devices.py | AUTOMATIC | 2022-10-22 | 1 | -9/+5 | |
| | | ||||||
| * | implement CUDA device selection by ID | Extraltodeus | 2022-10-21 | 1 | -3/+18 | |
| | | ||||||
| * | Add 'interrogate' and 'all' choices to --use-cpu | brkirch | 2022-10-14 | 1 | -1/+1 | |
| | | | | | | * Add 'interrogate' and 'all' choices to --use-cpu * Change type for --use-cpu argument to str.lower, so that choices are case insensitive | |||||
| * | --no-half-vae | AUTOMATIC | 2022-10-10 | 1 | -1/+5 | |
| | | ||||||
| * | Merge branch 'master' into cpu-cmdline-opt | brkirch | 2022-10-04 | 1 | -0/+10 | |
| |\ | ||||||
| | * | send all three of GFPGAN's and codeformer's models to CPU memory instead of ↵ | AUTOMATIC | 2022-10-04 | 1 | -0/+10 | |
| | | | | | | | | | just one for #1283 | |||||
| * | | Add BSRGAN to --add-cpu | brkirch | 2022-10-04 | 1 | -1/+1 | |
| | | | ||||||
| * | | Add --use-cpu command line option | brkirch | 2022-10-04 | 1 | -3/+2 | |
| | | | | | | | | | Remove MPS detection to use CPU for GFPGAN / CodeFormer and add a --use-cpu command line option. | |||||
| * | | Merge branch 'master' into master | brkirch | 2022-10-04 | 1 | -2/+1 | |
| |\| | ||||||
| | * | initial support for training textual inversion | AUTOMATIC | 2022-10-02 | 1 | -2/+1 | |
| | | | ||||||
| * | | When device is MPS, use CPU for GFPGAN instead | brkirch | 2022-10-01 | 1 | -1/+1 | |
| |/ | | | | GFPGAN will not work if the device is MPS, so default to CPU instead. | |||||
| * | first attempt to produce crrect seeds in batch | AUTOMATIC | 2022-09-13 | 1 | -0/+10 | |
| | | ||||||
| * | changes for #294 | AUTOMATIC | 2022-09-12 | 1 | -0/+17 | |
| | | ||||||
| * | Allow TF32 in CUDA for increased performance #279 | AUTOMATIC | 2022-09-12 | 1 | -0/+11 | |
| | | ||||||
| * | add half() supporrt for CLIP interrogation | AUTOMATIC | 2022-09-11 | 1 | -0/+6 | |
| | | ||||||
| * | CLIP interrogator | AUTOMATIC | 2022-09-11 | 1 | -6/+10 | |
| | | ||||||
| * | Modular device management | Abdullah Barhoum | 2022-09-11 | 1 | -0/+12 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |