From 52a614d16e5dfbdbbe456f71c47d67241b0e57b9 Mon Sep 17 00:00:00 2001 From: sayakpaul Date: Thu, 17 Apr 2025 10:18:08 +0530 Subject: [PATCH] add note about use_duck_shape in auraflow docs. --- docs/source/en/api/pipelines/aura_flow.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/source/en/api/pipelines/aura_flow.md b/docs/source/en/api/pipelines/aura_flow.md index 50a67bed293c..52c74a3ac549 100644 --- 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/)).