Update README.md

README.md

@@ -5,6 +5,8 @@ pipeline_tag: image-to-video
 <p align="center">
   <img src="./demos/demo-01.gif" width="70%" /> 
   <img src="./demos/demo-02.gif" width="70%" />
+  <img src="./demos/demo-03.gif" width="70%" />
+
 </p>
 <p align="center">Samples generated by AnimateLCM-SVD-xt</p>
 
@@ -27,6 +29,9 @@ AnimateLCM-SVD-xt can generally produces demos with good quality in 4 steps with
 | 2 steps, cfg=1 | 4 steps, cfg=1 | 8 steps, cfg=1 |
 | ![Alt text 1](./demos/03-2.gif) | ![Alt text 2](./demos/03-4.gif) | ![Alt text 3](./demos/03-8.gif) |
 | 2 steps, cfg=1 | 4 steps, cfg=1 | 8 steps, cfg=1 |
-
+| ![Alt text 1](./demos/04-2.gif) | ![Alt text 2](./demos/04-4.gif) | ![Alt text 3](./demos/04-8.gif) |
+| 2 steps, cfg=1 | 4 steps, cfg=1 | 8 steps, cfg=1 |
+| ![Alt text 1](./demos/05-2.gif) | ![Alt text 2](./demos/05-4.gif) | ![Alt text 3](./demos/05-8.gif) |
+| 2 steps, cfg=1 | 4 steps, cfg=1 | 8 steps, cfg=1 |
 
 Please contact Fu-Yun Wang ([email protected]) for the inference code and the scheduler design.