| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2023-06-04 | fix the broken line for #10990 | AUTOMATIC | |
| 2023-06-03 | torch.cuda.is_available() check for SdOptimizationXformers | Vivek K. Vasishtha | |
| 2023-06-01 | revert default cross attention optimization to Doggettx | AUTOMATIC | |
| make --disable-opt-split-attention command line option work again | |||
| 2023-05-21 | Add a couple `from __future__ import annotations`es for Py3.9 compat | Aarni Koskela | |
| 2023-05-19 | Apply suggestions from code review | AUTOMATIC1111 | |
| Co-authored-by: Aarni Koskela <akx@iki.fi> | |||
| 2023-05-19 | fix linter issues | AUTOMATIC | |
| 2023-05-18 | make it possible for scripts to add cross attention optimizations | AUTOMATIC | |
| add UI selection for cross attention optimization | |||
| 2023-05-11 | Autofix Ruff W (not W605) (mostly whitespace) | Aarni Koskela | |
| 2023-05-10 | ruff auto fixes | AUTOMATIC | |
| 2023-05-10 | autofixes from ruff | AUTOMATIC | |
| 2023-05-08 | Fix for Unet NaNs | brkirch | |
| 2023-03-24 | Update sd_hijack_optimizations.py | FNSpd | |
| 2023-03-21 | Update sd_hijack_optimizations.py | FNSpd | |
| 2023-03-10 | sdp_attnblock_forward hijack | Pam | |
| 2023-03-10 | argument to disable memory efficient for sdp | Pam | |
| 2023-03-07 | scaled dot product attention | Pam | |
| 2023-01-25 | Add UI setting for upcasting attention to float32 | brkirch | |
| 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. | |||
| 2023-01-23 | better support for xformers flash attention on older versions of torch | AUTOMATIC | |
| 2023-01-21 | add --xformers-flash-attention option & impl | Takuma Mori | |
| 2023-01-21 | extra networks UI | AUTOMATIC | |
| rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | |||
| 2023-01-06 | Added license | brkirch | |
| 2023-01-06 | Change sub-quad chunk threshold to use percentage | brkirch | |
| 2023-01-06 | Add Birch-san's sub-quadratic attention implementation | brkirch | |
| 2022-12-20 | Use other MPS optimization for large q.shape[0] * q.shape[1] | brkirch | |
| Check if q.shape[0] * q.shape[1] is 2**18 or larger and use the lower memory usage MPS optimization if it is. This should prevent most crashes that were occurring at certain resolutions (e.g. 1024x1024, 2048x512, 512x2048). Also included is a change to check slice_size and prevent it from being divisible by 4096 which also results in a crash. Otherwise a crash can occur at 1024x512 or 512x1024 resolution. | |||
| 2022-12-10 | cleanup some unneeded imports for hijack files | AUTOMATIC | |
| 2022-12-10 | do not replace entire unet for the resolution hack | AUTOMATIC | |
| 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 | |||
| 2022-10-19 | Remove wrong self reference in CUDA support for invokeai | Cheka | |
| 2022-10-18 | Update sd_hijack_optimizations.py | C43H66N12O12S2 | |
| 2022-10-18 | readd xformers attnblock | C43H66N12O12S2 | |
| 2022-10-18 | delete xformers attnblock | C43H66N12O12S2 | |
| 2022-10-11 | Use apply_hypernetwork function | brkirch | |
| 2022-10-11 | Add InvokeAI and lstein to credits, add back CUDA support | brkirch | |
| 2022-10-11 | Add check for psutil | brkirch | |
| 2022-10-11 | Add cross-attention optimization from InvokeAI | brkirch | |
| * Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS) * Add command line option for it * Make it default when CUDA is unavailable | |||
| 2022-10-11 | rename hypernetwork dir to hypernetworks to prevent clash with an old ↵ | AUTOMATIC | |
| filename that people who use zip instead of git clone will have | |||
| 2022-10-11 | fixes related to merge | AUTOMATIC | |
| 2022-10-11 | replace duplicate code with a function | AUTOMATIC | |
| 2022-10-10 | remove functorch | C43H66N12O12S2 | |
| 2022-10-09 | Fix VRAM Issue by only loading in hypernetwork when selected in settings | Fampai | |
| 2022-10-08 | make --force-enable-xformers work without needing --xformers | AUTOMATIC | |
| 2022-10-08 | add fallback for xformers_attnblock_forward | AUTOMATIC | |
| 2022-10-08 | simplify xfrmers options: --xformers to enable and that's it | AUTOMATIC | |
| 2022-10-08 | emergency fix for xformers (continue + shared) | AUTOMATIC | |
| 2022-10-08 | Merge pull request #1851 from C43H66N12O12S2/flash | AUTOMATIC1111 | |
| xformers attention | |||
| 2022-10-08 | update sd_hijack_opt to respect new env variables | C43H66N12O12S2 | |
| 2022-10-08 | Update sd_hijack_optimizations.py | C43H66N12O12S2 | |
| 2022-10-08 | add xformers attnblock and hypernetwork support | C43H66N12O12S2 | |
| 2022-10-08 | Add hypernetwork support to split cross attention v1 | brkirch | |
| * Add hypernetwork support to split_cross_attention_forward_v1 * Fix device check in esrgan_model.py to use devices.device_esrgan instead of shared.device | |||
| 2022-10-08 | switch to the proper way of calling xformers | C43H66N12O12S2 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |