Update README

README.md

@@ -51,7 +51,7 @@ The model was presented in the paper [A Very Big Video Reasoning Suite](https://
 
 | Model | Base Architecture | Other Remarks |
 |-------|-------------------|---------------|
-| [VBVR-Wan2.1](https://huggingface.co/Video-Reason/VBVR-Wan2.1) | Wan2.1-I2V-14B-720P | Diffusers format |
+| [**VBVR-Wan2.1**](https://huggingface.co/Video-Reason/VBVR-Wan2.1) | Wan2.1-I2V-14B-720P | Diffusers format |
 | [VBVR-Wan2.2](https://huggingface.co/Video-Reason/VBVR-Wan2.2) | Wan2.2-I2V-A14B | Diffusers format |
 | [VBVR-Wan2.1-diffsynth](https://huggingface.co/Video-Reason/VBVR-Wan2.1-diffsynth) | Wan2.1-I2V-14B-720P | DiffSynth LoRA format |
 | [VBVR-Wan2.2-diffsynth](https://huggingface.co/Video-Reason/VBVR-Wan2.2-diffsynth) | Wan2.2-I2V-A14B | DiffSynth LoRA format |
@@ -120,6 +120,11 @@ In this release, we present
     <tr style="background:#F2F0EF;font-weight:700;text-align:center;">
       <td colspan="14"><em>Proprietary Models</em></td>
     </tr>
+    <tr>
+      <td><u>Seedance 2.0</u></td>
+      <td><u>0.544</u></td><td><strong>0.570</strong></td><td>0.593</td><td><u>0.498</u></td><td><strong>0.618</strong></td><td><u>0.514</u></td><td><strong>0.602</strong></td>
+      <td><u>0.517</u></td><td><strong>0.643</strong></td><td>0.398</td><td><u>0.492</u></td><td>0.427</td><td><strong>0.556</strong></td>
+    </tr>
     <tr>
       <td>Runway Gen-4 Turbo</td>
       <td>0.403</td><td>0.392</td><td>0.396</td><td>0.409</td><td>0.429</td><td>0.341</td><td>0.363</td>
@@ -127,34 +132,44 @@ In this release, we present
     </tr>
     <tr>
       <td><strong>Sora 2</strong></td>
-      <td><strong>0.546</strong></td><td><strong>0.569</strong></td><td><u>0.602</u></td>
-      <td><u>0.477</u></td><td><strong>0.581</strong></td><td><strong>0.572</strong></td>
-      <td><strong>0.597</strong></td><td><strong>0.523</strong></td>
+      <td><strong>0.546</strong></td><td><u>0.569</u></td><td><u>0.602</u></td>
+      <td>0.477</td><td><u>0.581</u></td><td><strong>0.572</strong></td>
+      <td><u>0.597</u></td><td><strong>0.523</strong></td>
       <td><u>0.546</u></td><td><strong>0.472</strong></td><td><strong>0.525</strong></td>
-      <td><strong>0.462</strong></td><td><strong>0.546</strong></td>
+      <td><strong>0.462</strong></td><td><u>0.546</u></td>
     </tr>
     <tr>
       <td>Kling 2.6</td>
-      <td>0.369</td><td>0.408</td><td>0.465</td><td>0.323</td><td>0.375</td><td>0.347</td><td><u>0.519</u></td>
+      <td>0.369</td><td>0.408</td><td>0.465</td><td>0.323</td><td>0.375</td><td>0.347</td><td>0.519</td>
       <td>0.330</td><td>0.528</td><td>0.135</td><td>0.272</td><td>0.356</td><td>0.359</td>
     </tr>
     <tr>
-      <td><u>Veo 3.1</u></td>
-      <td><u>0.480</u></td><td><u>0.531</u></td><td><strong>0.611</strong></td>
-      <td><strong>0.503</strong></td><td><u>0.520</u></td><td><u>0.444</u></td>
-      <td>0.510</td><td><u>0.429</u></td>
-      <td><strong>0.577</strong></td><td>0.277</td><td><u>0.420</u></td>
-      <td><u>0.441</u></td><td><u>0.404</u></td>
+      <td>Veo 3.1</td>
+      <td>0.480</td><td>0.531</td><td><strong>0.611</strong></td>
+      <td><strong>0.503</strong></td><td>0.520</td><td>0.444</td>
+      <td>0.510</td><td>0.429</td>
+      <td><u>0.577</u></td><td>0.277</td><td>0.420</td>
+      <td><u>0.441</u></td><td>0.404</td>
     </tr>
     <tr style="background:#F2F0EF;font-weight:700;text-align:center;">
       <td colspan="14"><em>Data Scaling Strong Baseline</em></td>
     </tr>
+    <tr>
+      <td><strong>VBVR-LTX2.3</strong></td>
+      <td>0.516</td><td>0.580</td><td>0.608</td><td>0.631</td><td>0.529</td><td>0.454</td><td>0.680</td>
+      <td>0.453</td><td>0.608</td><td>0.577</td><td><u>0.409</u></td><td>0.414</td><td><u>0.388</u></td>
+    </tr>
+    <tr>
+      <td><strong>VBVR-Wan2.1</strong></td>
+      <td><u>0.592</u></td><td><u>0.724</u></td><td><u>0.705</u></td><td><u>0.710</u></td><td><u>0.727</u></td><td><u>0.719</u></td><td><u>0.784</u></td>
+      <td><u>0.461</u></td><td><u>0.674</u></td><td><strong>0.592</strong></td><td>0.387</td><td><u>0.461</u></td><td>0.387</td>
+    </tr>
     <tr>
       <td><strong>VBVR-Wan2.2</strong></td>
       <td><strong>0.685</strong></td><td><strong>0.760</strong></td><td><strong>0.724</strong></td>
       <td><strong>0.750</strong></td><td><strong>0.782</strong></td><td><strong>0.745</strong></td>
       <td><strong>0.833</strong></td><td><strong>0.610</strong></td>
-      <td><strong>0.768</strong></td><td><strong>0.572</strong></td><td><strong>0.547</strong></td>
+      <td><strong>0.768</strong></td><td><u>0.572</u></td><td><strong>0.547</strong></td>
       <td><strong>0.618</strong></td><td><strong>0.615</strong></td>
     </tr>
   </tbody>

example.py

@@ -3,7 +3,6 @@
 VBVR-Wan2.1 Image-to-Video Inference Example
 
 Generate a video from a reference image using the VBVR-Wan2.1 model.
-Wan2.1 uses a single transformer with a CLIPVisionModel image encoder.
 
 Usage:
     python example.py --model_path /path/to/VBVR-Wan2.1