diff --git a/TeaCache4HunyuanVideo/README.md b/TeaCache4HunyuanVideo/README.md
index f0f6b24..d575451 100644
--- a/TeaCache4HunyuanVideo/README.md
+++ b/TeaCache4HunyuanVideo/README.md
@@ -1,17 +1,10 @@
 <!-- ## **TeaCache4HunyuanVideo** -->
 # TeaCache4HunyuanVideo
 
-[TeaCache](https://github.com/LiewFeng/TeaCache) can speedup [HunyuanVideo](https://github.com/Tencent/HunyuanVideo) 2x without much visual quality degradation, in a training-free manner.
+[TeaCache](https://github.com/LiewFeng/TeaCache) can speedup [HunyuanVideo](https://github.com/Tencent/HunyuanVideo) 2x without much visual quality degradation, in a training-free manner. The following video presents the videos generated by HunyuanVideo, TeaCache (1.6x speedup) and TeaCache (2.1x speedup).
 
+https://github.com/user-attachments/assets/7f75f4e2-3d7e-4762-9afe-c5cc3dcabe44
 
-<video width="3840"  controls>
-    <source src="../assets/TeaCache4HunYuanVideo.mp4" type="video/mp4">
-</video>
- <div style="display: grid; grid-template-columns: repeat(3, 1fr); gap: 10px; place-items: center; font-size: 1.2em;">
-        <div>HunyuanVideo, ~50 min</div>
-        <div>TeaCache (0.1), ~30 min</div>
-        <div>TeaCache (0.15), <font color="#FF0000">~23 min</font></div>
-</div>
 
 ## 📈 Inference Latency Comparisons on a Single A800 GPU