OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-04-27 15:29:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

basic --opt-sdp-attention info derived from discussion post https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/8691

ClashSAN 2023-03-22 14:18:09 +00:00
parent 5ffbfa4cf4
commit c06be1b1e7
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Optimizations.md

@ -2,7 +2,9 @@ A number of optimization can be enabled by [commandline arguments](Run-with-Cust
| commandline argument | explanation |
|--------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `--xformers` | Use [xformers](https://github.com/facebookresearch/xformers) library. Great improvement to memory consumption and speed. Windows version installs binaries mainained by [C43H66N12O12S2](https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases). Will only be enabled on small subset of configuration because that's what we have binaries for. [Documentation](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers) |
| `--opt-sdp-attention` | Faster speeds than using xformers, only available for user who manually install torch 2.0 to their venv. (non-deterministic)
| `--opt-sdp-no-mem-attention` | Faster speeds than using xformers, only available for user who manually install torch 2.0 to their venv. (deterministic, slight slower than `--opt-sdp-attention`)
| `--xformers` | Use [xformers](https://github.com/facebookresearch/xformers) library. Great improvement to memory consumption and speed. Will only be enabled on small subset of configuration because that's what we have binaries for. [Documentation](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers) |
| `--force-enable-xformers` | Enables xformers above regardless of whether the program thinks you can run it or not. Do not report bugs you get running this. |
| `--opt-split-attention` | Cross attention layer optimization significantly reducing memory use for almost no cost (some report improved performance with it). Black magic. <br/>On by default for `torch.cuda`, which includes both NVidia and AMD cards. |
| `--disable-opt-split-attention` | Disables the optimization above. |