Update README.md

README.md

@@ -67,7 +67,7 @@ For VAE, the LightX2V team has conducted a series of deep optimizations, derivin
 **Features**: Best Balanced Solution ⚖️
 
 ✅ Uses **Causal 3D Conv** (same as official)  
-✅ **Quality close to official** ⭐⭐⭐⭐⭐  
+✅ **Quality close to official** ⭐⭐⭐⭐
 ✅ Memory reduced by **~50%** (~4-5 GB)  
 ✅ Speed increased by **2-3x**  
 ✅ Balances quality, speed, and memory 🏆
@@ -80,7 +80,7 @@ For VAE, the LightX2V team has conducted a series of deep optimizations, derivin
 
 ✅ Minimal memory usage (~0.4 GB)  
 ✅ Extremely fast inference  
-✅ **Quality close to official** ⭐⭐⭐⭐⭐  
+✅ **Quality close to official** ⭐⭐⭐⭐
 ✅ **Significantly surpasses open source TAE**
 
 </td>
@@ -136,24 +136,23 @@ Model: seko-talk
 <tr>
 <td width="25%" align="center">
 <strong>Wan2.1_VAE</strong><br>
-<video controls autoplay width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/6l-P-3Hr9JKL3xgUyJXWJ.mp4"></video>
+<video controls autoplay muted width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/6l-P-3Hr9JKL3xgUyJXWJ.mp4"></video>
 </td>
 <td width="25%" align="center">
 <strong>taew2_1</strong><br>
-<video controls autoplay width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/rcVHrCKB4nRAs2VSjJd2d.mp4"></video>
+<video controls autoplay muted width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/rcVHrCKB4nRAs2VSjJd2d.mp4"></video>
 </td>
 <td width="25%" align="center">
 <strong>lighttaew2_1</strong><br>
-<video controls autoplay width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/Wq9p9Z7NDYwaKw4SqVbYT.mp4"></video>
+<video controls autoplay muted width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/Wq9p9Z7NDYwaKw4SqVbYT.mp4"></video>
 </td>
 <td width="25%" align="center">
 <strong>lightvaew2_1</strong><br>
-<video controls autoplay width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/NpKOzFcvsHzSFfFACzUKP.mp4"></video>
+<video controls autoplay muted width="100%" src="https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/NpKOzFcvsHzSFfFACzUKP.mp4"></video>
 </td>
 </tr>
 </table>
 
-
 ##  📊 Wan2.2 Series Performance Comparison
 - **Precision**: BF16
 - **Test Hardware**: NVIDIA H100
@@ -221,7 +220,7 @@ Model: [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B)
 - ✅ **Excellent quality**, close to official
 - ✅ Memory reduced by **~50%** (~4-5 GB)
 - ✅ Speed increased by **2-3x**
-- ✅ **Close to official quality** ⭐⭐⭐⭐⭐
+- ✅ **Close to official quality** ⭐⭐⭐⭐
 
 **Use Cases**: Daily production, strongly recommended ⭐
 
@@ -234,7 +233,7 @@ Model: [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B)
 - ✅ Extremely low memory usage (~0.4 GB)
 - ✅ Extremely fast inference
 - ✅ **Quality significantly surpasses open source TAE**
-- ✅ **Close to official quality** ⭐⭐⭐⭐⭐
+- ✅ **Close to official quality** ⭐⭐⭐⭐
 
 **Use Cases**: Development testing, rapid iteration
 
@@ -250,11 +249,11 @@ Model: [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B)
 | **Architecture** | Conv2D | Conv2D | Causal Conv3D | Causal Conv3D |
 | **Memory Usage** | Minimal (~0.4 GB) | Minimal (~0.4 GB) | Large (~8-12 GB) | Medium (~4-5 GB) |
 | **Inference Speed** | Extremely Fast ⚡⚡⚡⚡⚡ | Extremely Fast ⚡⚡⚡⚡⚡ | Slow ⚡⚡ | Fast ⚡⚡⚡⚡ |
-| **Generation Quality** | Average ⭐⭐⭐ | **Close to Official** ⭐⭐⭐⭐⭐ | Highest ⭐⭐⭐⭐⭐ |  **Close to Official** ⭐⭐⭐⭐⭐  |
+| **Generation Quality** | Average ⭐⭐⭐ | **Close to Official** ⭐⭐⭐⭐ | Highest ⭐⭐⭐⭐⭐ |  **Close to Official** ⭐⭐⭐⭐  |
 
 ## 📑 Todo List
   - [x] LightX2V integration
-  - [ ] ComfyUI integration
+  - [x] ComfyUI integration
   - [ ] Training & Distillation Code
   
 ## 🚀 Usage
@@ -397,6 +396,10 @@ cd LightX2V/scripts
 bash wan/run_wan_i2v.sh  # or other inference scripts
 ```
 
+### Use in ComfyUI
+
+please refer to  https://github.com/ModelTC/ComfyUI-LightVAE
+
 ## ⚠️ Important Notes
 
 ### 1. Compatibility