Age | Commit message (Collapse) | Author | |
---|---|---|---|
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. | |||
2022-12-03 | add built-in extension system | AUTOMATIC | |
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 | |
2022-12-03 | fix #4407 breaking UI entirely for card other than ones related to the PR | AUTOMATIC | |
2022-12-03 | Merge pull request #4407 from yoinked-h/patch-1 | AUTOMATIC1111 | |
Fix issue with 16xx cards | |||
2022-11-30 | Rework MPS randn fix, add randn_like fix | brkirch | |
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. | |||
2022-11-27 | Merge pull request #4918 from brkirch/pytorch-fixes | AUTOMATIC1111 | |
Fixes for PyTorch 1.12.1 when using MPS | |||
2022-11-27 | eliminate duplicated code from #5095 | AUTOMATIC | |
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. | |||
2022-11-21 | 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) | |||
2022-11-17 | Revert "MPS Upscalers Fix" | brkirch | |
This reverts commit 768b95394a8500da639b947508f78296524f1836. | |||
2022-11-12 | change formatting to match the main program in devices.py | AUTOMATIC | |
2022-11-12 | Update devices.py | 源文雨 | |
2022-11-12 | Fix wrong mps selection below MasOS 12.3 | 源文雨 | |
2022-11-08 | actual better fix | pepe10-gpu | |
thanks C43H66N12O12S2 | |||
2022-11-07 | terrible hack | pepe10-gpu | |
2022-11-06 | 16xx card fix | pepe10-gpu | |
cudnn | |||
2022-10-25 | MPS Upscalers Fix | brkirch | |
Get ESRGAN, SCUNet, and SwinIR working correctly on MPS by ensuring memory is contiguous for tensor views before sending to MPS device. | |||
2022-10-25 | Remove BSRGAN from --use-cpu, add SwinIR | brkirch | |
2022-10-22 | remove parsing command line from devices.py | AUTOMATIC | |
2022-10-22 | implement CUDA device selection by ID | Extraltodeus | |
2022-10-14 | Add 'interrogate' and 'all' choices to --use-cpu | brkirch | |
* Add 'interrogate' and 'all' choices to --use-cpu * Change type for --use-cpu argument to str.lower, so that choices are case insensitive | |||
2022-10-10 | --no-half-vae | AUTOMATIC | |
2022-10-04 | Merge branch 'master' into cpu-cmdline-opt | brkirch | |
2022-10-04 | send all three of GFPGAN's and codeformer's models to CPU memory instead of ↵ | AUTOMATIC | |
just one for #1283 | |||
2022-10-04 | Add BSRGAN to --add-cpu | brkirch | |
2022-10-04 | Add --use-cpu command line option | brkirch | |
Remove MPS detection to use CPU for GFPGAN / CodeFormer and add a --use-cpu command line option. | |||
2022-10-04 | Merge branch 'master' into master | brkirch | |
2022-10-02 | initial support for training textual inversion | AUTOMATIC | |
2022-09-30 | When device is MPS, use CPU for GFPGAN instead | brkirch | |
GFPGAN will not work if the device is MPS, so default to CPU instead. | |||
2022-09-13 | first attempt to produce crrect seeds in batch | AUTOMATIC | |
2022-09-12 | changes for #294 | AUTOMATIC | |
2022-09-12 | Allow TF32 in CUDA for increased performance #279 | AUTOMATIC | |
2022-09-11 | add half() supporrt for CLIP interrogation | AUTOMATIC | |
2022-09-11 | CLIP interrogator | AUTOMATIC | |
2022-09-11 | Modular device management | Abdullah Barhoum | |