aidenyzhang commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,14 +6,16 @@ Yue Zhang <sup>\*</sup>,
|
|
| 6 |
Minhao Liu<sup>\*</sup>,
|
| 7 |
Zhaokang Chen,
|
| 8 |
Bin Wu<sup>†</sup>,
|
| 9 |
-
|
| 10 |
Chao Zhan,
|
|
|
|
|
|
|
| 11 |
Wenjiang Zhou
|
| 12 |
(<sup>*</sup>Equal Contribution, <sup>†</sup>Corresponding Author, benbinwu@tencent.com)
|
| 13 |
|
| 14 |
Lyra Lab, Tencent Music Entertainment
|
| 15 |
|
| 16 |
-
**[github](https://github.com/TMElyralab/MuseTalk)** **[huggingface](https://huggingface.co/TMElyralab/MuseTalk)** **[space](https://huggingface.co/spaces/TMElyralab/MuseTalk)** **
|
| 17 |
|
| 18 |
We introduce `MuseTalk`, a **real-time high quality** lip-syncing model (30fps+ on an NVIDIA Tesla V100). MuseTalk can be applied with input videos, e.g., generated by [MuseV](https://github.com/TMElyralab/MuseV), as a complete virtual human solution.
|
| 19 |
|
|
@@ -41,7 +43,8 @@ Please find details in the following two links or contact zkangchen@tencent.com
|
|
| 41 |
# News
|
| 42 |
- [04/02/2024] Release MuseTalk project and pretrained models.
|
| 43 |
- [04/16/2024] Release Gradio [demo](https://huggingface.co/spaces/TMElyralab/MuseTalk) on HuggingFace Spaces (thanks to HF team for their community grant)
|
| 44 |
-
- [04/17/2024] :
|
|
|
|
| 45 |
|
| 46 |
## Model
|
| 47 |

|
|
@@ -319,7 +322,7 @@ If you need higher resolution, you could apply super resolution models such as [
|
|
| 319 |
```bib
|
| 320 |
@article{musetalk,
|
| 321 |
title={MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting},
|
| 322 |
-
author={Zhang, Yue and Liu, Minhao and Chen, Zhaokang and Wu, Bin and
|
| 323 |
journal={arxiv},
|
| 324 |
year={2024}
|
| 325 |
}
|
|
|
|
| 6 |
Minhao Liu<sup>\*</sup>,
|
| 7 |
Zhaokang Chen,
|
| 8 |
Bin Wu<sup>†</sup>,
|
| 9 |
+
Yubin Zeng,
|
| 10 |
Chao Zhan,
|
| 11 |
+
Yingjie He,
|
| 12 |
+
Junxin Huang,
|
| 13 |
Wenjiang Zhou
|
| 14 |
(<sup>*</sup>Equal Contribution, <sup>†</sup>Corresponding Author, benbinwu@tencent.com)
|
| 15 |
|
| 16 |
Lyra Lab, Tencent Music Entertainment
|
| 17 |
|
| 18 |
+
**[github](https://github.com/TMElyralab/MuseTalk)** **[huggingface](https://huggingface.co/TMElyralab/MuseTalk)** **[space](https://huggingface.co/spaces/TMElyralab/MuseTalk)** **[Technical report](https://arxiv.org/pdf/2410.10122)**
|
| 19 |
|
| 20 |
We introduce `MuseTalk`, a **real-time high quality** lip-syncing model (30fps+ on an NVIDIA Tesla V100). MuseTalk can be applied with input videos, e.g., generated by [MuseV](https://github.com/TMElyralab/MuseV), as a complete virtual human solution.
|
| 21 |
|
|
|
|
| 43 |
# News
|
| 44 |
- [04/02/2024] Release MuseTalk project and pretrained models.
|
| 45 |
- [04/16/2024] Release Gradio [demo](https://huggingface.co/spaces/TMElyralab/MuseTalk) on HuggingFace Spaces (thanks to HF team for their community grant)
|
| 46 |
+
- [04/17/2024] : We release a pipeline that utilizes MuseTalk for real-time inference.
|
| 47 |
+
- [10/18/2024] :mega: We publish the [technical report](https://arxiv.org/pdf/2410.10122).
|
| 48 |
|
| 49 |
## Model
|
| 50 |

|
|
|
|
| 322 |
```bib
|
| 323 |
@article{musetalk,
|
| 324 |
title={MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting},
|
| 325 |
+
author={Zhang, Yue and Liu, Minhao and Chen, Zhaokang and Wu, Bin and Zeng, Yubin and Zhan, Chao and He, Yingjie and Huang, Junxin and Zhou, Wenjiang},
|
| 326 |
journal={arxiv},
|
| 327 |
year={2024}
|
| 328 |
}
|