Updated Optimizations (markdown)

AUTOMATIC1111 2022-10-08 20:00:40 +03:00
parent 468ec85373
commit aa4b47bd5f

@ -1,8 +1,9 @@
A number of optimization can be enabled by [commandline arguments](Run-with-Custom-Parameters): A number of optimization can be enabled by [commandline arguments](Run-with-Custom-Parameters):
| commandline argument | explanation | | 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). | | `--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. |
| `--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 preformance with it). Black magic. <br/>On by default for `torch.cuda`, which includes both NVidia and AMD cards. | | `--opt-split-attention` | Cross attention layer optimization significantly reducing memory use for almost no cost (some report improved preformance 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. | | `--disable-opt-split-attention` | Disables the optimization above. |
| `--opt-split-attention-v1` | Uses an older version of the optimization above that is not as memory hungry (it will use less VRAM, but will be more limiting in the maximum size of pictures you can make). | | `--opt-split-attention-v1` | Uses an older version of the optimization above that is not as memory hungry (it will use less VRAM, but will be more limiting in the maximum size of pictures you can make). |