Hanbo-Cheng commited on
Commit
12f798d
·
verified ·
1 Parent(s): 331a927

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -23
README.md CHANGED
@@ -1,23 +1,22 @@
1
- ---
2
- license: mit
3
- ---
4
- # 🌅 DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation
5
-
6
- [![arXiv](https://img.shields.io/badge/Arxiv-2410.13726-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2410.13726)
7
- [![Demo Page](https://img.shields.io/badge/Demo_Page-blue)](https://hanbo-cheng.github.io/DAWN/)
8
- [![zhihu](https://img.shields.io/badge/知乎-0079FF.svg?logo=zhihu&logoColor=white)](https://zhuanlan.zhihu.com/p/2253009511)
9
- [![DAWN](https://img.shields.io/badge/Github-181717?style=plastic&logo=github&logoColor=white)](https://github.com/Hanbo-Cheng/DAWN-pytorch)
10
-
11
- `./hubert_ckpt`: hubert audio encoder, same as [hubert-base](https://huggingface.co/facebook/hubert-base-ls960)
12
-
13
- `./pbnet_both/checkpoint_100000.pth.tar`: checkpoint for the Pose-Blink generation network
14
-
15
- `DAWN_128.pth`: checkpoint for the A2V-FDM with 128 * 128 resolution
16
-
17
- `DAWN_256.pth`: checkpoint for the A2V-FDM with 256 * 256 resolution
18
-
19
- `LFG_128_1000ep.pth`: checkpoint for the LFG with 128 * 128 resolution
20
-
21
- `LFG_256_400ep.pth`: checkpoint for the LFG with 256 * 256 resolution
22
-
23
-
 
1
+ ---
2
+ license: mit
3
+ pipeline_tag: image-to-video
4
+ ---
5
+ # 🌅 DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation
6
+
7
+ [![arXiv](https://img.shields.io/badge/Arxiv-2410.13726-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2410.13726)
8
+ [![Demo Page](https://img.shields.io/badge/Demo_Page-blue)](https://hanbo-cheng.github.io/DAWN/)
9
+ [![zhihu](https://img.shields.io/badge/知乎-0079FF.svg?logo=zhihu&logoColor=white)](https://zhuanlan.zhihu.com/p/2253009511)
10
+ [![DAWN](https://img.shields.io/badge/Github-181717?style=plastic&logo=github&logoColor=white)](https://github.com/Hanbo-Cheng/DAWN-pytorch)
11
+
12
+ `./hubert_ckpt`: hubert audio encoder, same as [hubert-base](https://huggingface.co/facebook/hubert-base-ls960)
13
+
14
+ `./pbnet_both/checkpoint_100000.pth.tar`: checkpoint for the Pose-Blink generation network
15
+
16
+ `DAWN_128.pth`: checkpoint for the A2V-FDM with 128 * 128 resolution
17
+
18
+ `DAWN_256.pth`: checkpoint for the A2V-FDM with 256 * 256 resolution
19
+
20
+ `LFG_128_1000ep.pth`: checkpoint for the LFG with 128 * 128 resolution
21
+
22
+ `LFG_256_400ep.pth`: checkpoint for the LFG with 256 * 256 resolution