From a19f9029aaa978ae90a7a769f65be180cc083dd1 Mon Sep 17 00:00:00 2001
From: Sayak Paul <spsayakpaul@gmail.com>
Date: Thu, 23 Jan 2025 12:07:25 +0530
Subject: [PATCH] fix image path in para attention docs

---
 docs/source/en/optimization/para_attn.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/source/en/optimization/para_attn.md b/docs/source/en/optimization/para_attn.md
index b1b111045590..94b0d5ce3af4 100644
--- a/docs/source/en/optimization/para_attn.md
+++ b/docs/source/en/optimization/para_attn.md
@@ -29,7 +29,7 @@ However, it is hard to decide when to reuse the cache to ensure quality generate
 This achieves a 2x speedup on FLUX.1-dev and HunyuanVideo inference with very good quality.
 
 <figure>
-    <img src="https://huggingface.co/datasets/chengzeyi/documentation-images/resolve/main/diffusers/para-attn/ada-cache.png" alt="Cache in Diffusion Transformer" />
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/para-attn/ada-cache.png" alt="Cache in Diffusion Transformer" />
     <figcaption>How AdaCache works, First Block Cache is a variant of it</figcaption>
 </figure>