Update README.md

README.md

@@ -2,6 +2,13 @@
 pipeline_tag: image-to-video
 ---
 
+<p align="center">
+  <img src="./demos/demo-01.gif" width="40%" /> 
+  <img src="./demos/demo-02.gif" width="40%" />
+</p>
+<p align="center">Samples generated by AnimateLCM-SVD-xt</p>
+
+
 ## Introduction
 Consistency Distilled [Stable Video Diffusion Image2Video-XT (SVD-xt)](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt) following the strategy proposed in [AnimateLCM-paper](https://arxiv.org/abs/2402.00769).
 AnimateLCM-SVD-xt can generate good quality image-conditioned videos with 25 frames in 2~8 steps with 576x1024 resolutions.
@@ -12,6 +19,14 @@ AnimateLCM-SVD-xt can generally produces demos with good quality in 4 steps with
 
 ## Demos
 
+|     |     |     |
+| :---: | :---: | :---: |
+| ![Alt text 1](./demos/01-2.gif) | ![Alt text 2](./demos/01-4.gif) | ![Alt text 3](./demos/01-8.gif) |
+| 2 steps, cfg=1 | 4 steps, cfg=1 | 8 steps, cfg=1 |
+| ![Alt text 1](./demos/02-2.gif) | ![Alt text 2](./demos/02-4.gif) | ![Alt text 3](./demos/02-8.gif) |
+| 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 |
 
 
 Please contact Fu-Yun Wang ([email protected]) for the inference code and the scheduler design.