Spaces:
Running
Running
Muyao Niu
commited on
Commit
·
21178a8
1
Parent(s):
7d0821f
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,11 +12,11 @@
|
|
| 12 |
|
| 13 |
## Introduction
|
| 14 |
<p align="center">
|
| 15 |
-
<img src="assets/
|
| 16 |
</p>
|
| 17 |
We introduce MOFA-Video, a method designed to adapt motions from different domains to the frozen Video Diffusion Model. By employing <u>sparse-to-dense (S2D) motion generation</u> and <u>flow-based motion adaptation</u>, MOFA-Video can effectively animate a single image using various types of control signals, including trajectories, keypoint sequences, AND their combinations.
|
| 18 |
<p align="center">
|
| 19 |
-
<img src="assets/
|
| 20 |
</p>
|
| 21 |
During the training stage, we generate sparse control signals through sparse motion sampling and then train different MOFA-Adapters to generate video via pre-trained SVD. During the inference stage, different MOFA-Adapters can be combined to jointly control the frozen SVD.
|
| 22 |
|
|
|
|
| 12 |
|
| 13 |
## Introduction
|
| 14 |
<p align="center">
|
| 15 |
+
<img src="assets/images/project-mofa.png">
|
| 16 |
</p>
|
| 17 |
We introduce MOFA-Video, a method designed to adapt motions from different domains to the frozen Video Diffusion Model. By employing <u>sparse-to-dense (S2D) motion generation</u> and <u>flow-based motion adaptation</u>, MOFA-Video can effectively animate a single image using various types of control signals, including trajectories, keypoint sequences, AND their combinations.
|
| 18 |
<p align="center">
|
| 19 |
+
<img src="assets/images/pipeline.png">
|
| 20 |
</p>
|
| 21 |
During the training stage, we generate sparse control signals through sparse motion sampling and then train different MOFA-Adapters to generate video via pre-trained SVD. During the inference stage, different MOFA-Adapters can be combined to jointly control the frozen SVD.
|
| 22 |
|