hoelee/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-08-03 10:50:23 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

make it possible for scripts to add cross attention optimizations

Browse Source 
add UI selection for cross attention optimization
This commit is contained in:
AUTOMATIC
2023-05-18 22:48:28 +03:00
parent 2e006fa500
commit 2582a0fd3b
7 changed files with 226 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
modules/cmd_args.py
View File

@@ -53,16 +53,16 @@ parser.add_argument("--xformers", action='store_true', help="enable xformers for
parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
parser.add_argument("--xformers-flash-attention", action='store_true', help="enable xformers with Flash Attention to improve reproducibility (supported for SD2.x or variant only)")
parser.add_argument("--deepdanbooru", action='store_true', help="does not do anything")
parser.add_argument("--opt-split-attention", action='store_true', help="force-enables Doggettx's cross-attention layer optimization. By default, it's on for torch cuda.")
parser.add_argument("--opt-sub-quad-attention", action='store_true', help="enable memory efficient sub-quadratic cross-attention layer optimization")
parser.add_argument("--opt-split-attention", action='store_true', help="prefer Doggettx's cross-attention layer optimization for automatic choice of optimization")
parser.add_argument("--opt-sub-quad-attention", action='store_true', help="prefer memory efficient sub-quadratic cross-attention layer optimization for automatic choice of optimization")
parser.add_argument("--sub-quad-q-chunk-size", type=int, help="query chunk size for the sub-quadratic cross-attention layer optimization to use", default=1024)
parser.add_argument("--sub-quad-kv-chunk-size", type=int, help="kv chunk size for the sub-quadratic cross-attention layer optimization to use", default=None)
parser.add_argument("--sub-quad-chunk-threshold", type=int, help="the percentage of VRAM threshold for the sub-quadratic cross-attention layer optimization to use chunking", default=None)
parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
parser.add_argument("--opt-sdp-attention", action='store_true', help="enable scaled dot product cross-attention layer optimization; requires PyTorch 2.*")
parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="enable scaled dot product cross-attention layer optimization without memory efficient attention, makes image generation deterministic; requires PyTorch 2.*")
parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="prefer InvokeAI's cross-attention layer optimization for automatic choice of optimization")
parser.add_argument("--opt-split-attention-v1", action='store_true', help="prefer older version of split attention optimization for automatic choice of optimization")
parser.add_argument("--opt-sdp-attention", action='store_true', help="prefer scaled dot product cross-attention layer optimization for automatic choice of optimization; requires PyTorch 2.*")
parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="prefer scaled dot product cross-attention layer optimization without memory efficient attention for automatic choice of optimization, makes image generation deterministic; requires PyTorch 2.*")
parser.add_argument("--disable-opt-split-attention", action='store_true', help="does not do anything")
parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")