Update README.md

README.md

@@ -58,20 +58,6 @@ For VAE, the LightX2V team has conducted a series of deep optimizations, derivin
 ❌ Average quality ⭐⭐⭐  
 ❌ Potential detail loss
 
-</td>
-</tr>
-<tr>
-<td width="50%">
-
-### 🎯 **LightVAE Series** (Our Optimization)
-**Features**: Best Balanced Solution ⚖️
-
-✅ Uses **Causal 3D Conv** (same as official)  
-✅ **High accuracy ceiling** ⭐⭐⭐⭐⭐  
-✅ Memory reduced by **~50%** (~4-5 GB)  
-✅ Speed increased by **2-3x**  
-✅ Balances quality, speed, and memory 🏆
-
 </td>
 <td width="50%">
 
@@ -80,13 +66,29 @@ 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>
 </tr>
 </table>
 
+
+</td>
+</tr>
+<tr>
+<td width="50%">
+
+### 🎯 **LightVAE Series** (Our Optimization)
+**Features**: Best Balanced Solution ⚖️
+
+✅ Uses **Causal 3D Conv** (same as official)  
+✅ **Quality close to official** ⭐⭐⭐⭐⭐  
+✅ Memory reduced by **~50%** (~4-5 GB)  
+✅ Speed increased by **2-3x**  
+✅ Balances quality, speed, and memory 🏆
+
+
 ---
 
 ## 📦 Available Models
@@ -221,7 +223,7 @@ Model: [Wan-AI/Wan2.1-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.1-T2V-A14B)
 - ✅ **Excellent quality**, close to official
 - ✅ Memory reduced by **~50%** (~4-5 GB)
 - ✅ Speed increased by **2-3x**
-- ✅ **High accuracy ceiling**
+- ✅ **Close to official quality** ⭐⭐⭐⭐⭐
 
 **Use Cases**: Daily production, strongly recommended ⭐
 
@@ -234,7 +236,7 @@ Model: [Wan-AI/Wan2.1-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.1-T2V-A14B)
 - ✅ 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
 
@@ -250,8 +252,7 @@ Model: [Wan-AI/Wan2.1-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.1-T2V-A14B)
 | **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 ⭐⭐⭐⭐⭐ | Excellent ⭐⭐⭐⭐⭐ |
-| **Accuracy Ceiling** | Medium | Medium | Highest | **High** |
+| **Generation Quality** | Average ⭐⭐⭐ | **Close to Official** ⭐⭐⭐⭐⭐ | Highest ⭐⭐⭐⭐⭐ |  **Close to Official** ⭐⭐⭐⭐⭐  |
 
 ## 🚀 Usage