[docs] add note about use_duck_shape in auraflow docs. (#11348)

add note about use_duck_shape in auraflow docs.

[docs] add note about use_duck_shape in auraflow docs. (#11348)
add note about use_duck_shape in auraflow docs.
b00a564d · Sayak Paul · GitHub · efc9d68b · b00a564d
Unverified Commit b00a564d authored Apr 17, 2025 by Sayak Paul Committed by GitHub Apr 17, 2025
Show whitespace changes
Inline Side-by-side

Showing with 2 additions and 0 deletions

docs/source/en/api/pipelines/aura_flow.md docs/source/en/api/pipelines/aura_flow.md +2 -0

No files found.
--- a/docs/source/en/api/pipelines/aura_flow.md
+++ b/docs/source/en/api/pipelines/aura_flow.md
@@ -100,6 +100,8 @@ AuraFlow can be compiled with `torch.compile()` to speed up inference latency ev
 )
 ```

+Specifying `use_duck_shape` to be `False` instructs the compiler if it should use the same symbolic variable to represent input sizes that are the same. For more details, check out [this comment](https://github.com/huggingface/diffusers/pull/11327#discussion_r2047659790).
+
 This enables from 100% (on low resolutions) to a 30% (on 1536x1536 resolution) speed improvements.

 Thanks to [AstraliteHeart](https://github.com/huggingface/diffusers/pull/11297/) who helped us rewrite the [`AuraFlowTransformer2DModel`] class so that the above works for different resolutions ([PR](https://github.com/huggingface/diffusers/pull/11297/)).