diff --git a/README.md b/README.md
index 204fbf2..114c54c 100644
--- a/README.md
+++ b/README.md
@@ -48,7 +48,7 @@ Existing autoregressive large-scale text-to-speech (TTS) models have advantages
 
 **IndexTTS2: The Future of Voice, Now Generating**
 
-[![IndexTTS2 Demo](assets/IndexTTS2-video-pic.png)](assets/IndexTTS2.mp4)
+[![IndexTTS2 Demo](assets/IndexTTS2-video-pic.png)](https://www.bilibili.com/video/BV136a9zqEk5)
 
 *Click the image to watch IndexTTS2 video*
 
@@ -132,6 +132,11 @@ Recommended for China users. 如果下载速度慢，可以使用镜像：
 export HF_ENDPOINT="https://hf-mirror.com"
 ```
 
+Or download by `modelscope`
+```bash
+modelscope download --model IndexTeam/IndexTTS-2 --local_dir checkpoints
+```
+
 
 ### IndexTTS2 Quickstart
 
diff --git a/assets/IndexTTS2.mp4 b/assets/IndexTTS2.mp4
deleted file mode 100644
index 104770b..0000000
Binary files a/assets/IndexTTS2.mp4 and /dev/null differ