Instructions to use Wan-AI/Wan-Dancer-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan-Dancer-14B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan-Dancer-14B", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ tags:
|
|
| 17 |
<p>
|
| 18 |
|
| 19 |
<p align="center">
|
| 20 |
-
π <a href="https://humanaigc.github.io/wan-dancer-project/"><b>
|
| 21 |
<br>
|
| 22 |
|
| 23 |
|
|
@@ -25,7 +25,7 @@ tags:
|
|
| 25 |
|
| 26 |
|
| 27 |
## π₯ Latest News!!
|
| 28 |
-
* July 13, 2026: π We introduce **[Wan-Dancer](https://humanaigc.github.io/wan-dancer/)**, a method can generate long-duration, high-quality, rhythmic dance videos from music with global structure and temporal continuity. We released the [model weights](#model-download) and [inference code](https://github.com/Wan-Video/Wan-Dancer). And now you can try it on [ModelScope Studio](https://www.modelscope.cn/studios/Wan-AI/Wan-Dancer) or [HuggingFace Space](https://huggingface.co/spaces/Wan-AI/Wan-Dancer)!
|
| 29 |
|
| 30 |
|
| 31 |
## π Todo List
|
|
@@ -154,11 +154,14 @@ If you use this code or framework in your research, please cite:
|
|
| 154 |
|
| 155 |
```bibtex
|
| 156 |
@article{wan-dancer-2026,
|
| 157 |
-
title={Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation},
|
| 158 |
-
author={Mingyang
|
| 159 |
-
|
| 160 |
-
|
| 161 |
-
|
|
|
|
|
|
|
|
|
|
| 162 |
}
|
| 163 |
```
|
| 164 |
|
|
@@ -171,5 +174,5 @@ This project is licensed under the Apache 2.0 License β see the [LICENSE](LICE
|
|
| 171 |
This work builds upon and integrates components from the following open-source projects:
|
| 172 |
|
| 173 |
1. [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
|
| 174 |
-
2. [Wan2.1](https://github.com/Wan-Video/Wan2.1)
|
| 175 |
|
|
|
|
| 17 |
<p>
|
| 18 |
|
| 19 |
<p align="center">
|
| 20 |
+
π <a href="https://humanaigc.github.io/wan-dancer-project/"><b>Project</b></a>    ο½    π₯οΈ <a href="https://github.com/Wan-Video/Wan-Dancer">GitHub</a>    |   π€ <a href="https://modelscope.ai/studios/Wan-AI/Wan-Dancer">MS Space</a>   |   π€ <a href="https://www.modelscope.cn/models/Wan-AI/Wan-Dancer-14B">MS Model</a>   |   π€ <a href="https://huggingface.co/Wan-AI/Wan-Dancer-14B">HF Model</a>   |    π <a href="https://arxiv.org/abs/2607.09581">Paper</a>   
|
| 21 |
<br>
|
| 22 |
|
| 23 |
|
|
|
|
| 25 |
|
| 26 |
|
| 27 |
## π₯ Latest News!!
|
| 28 |
+
* July 13, 2026: π We introduce **[Wan-Dancer](https://humanaigc.github.io/wan-dancer-project/)**, a method can generate long-duration, high-quality, rhythmic dance videos from music with global structure and temporal continuity. We released the [model weights](#model-download) and [inference code](https://github.com/Wan-Video/Wan-Dancer). And now you can try it on [ModelScope Studio](https://www.modelscope.cn/studios/Wan-AI/Wan-Dancer) or [HuggingFace Space](https://huggingface.co/spaces/Wan-AI/Wan-Dancer)!
|
| 29 |
|
| 30 |
|
| 31 |
## π Todo List
|
|
|
|
| 154 |
|
| 155 |
```bibtex
|
| 156 |
@article{wan-dancer-2026,
|
| 157 |
+
title = {Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation},
|
| 158 |
+
author = {Huang, Mingyang and Zhang, Peng and Hu, Li and Wang, Guangyuan and Zhang, Ruoshi and Lu, Yi and Cheng, Gang and Zhang, Bang},
|
| 159 |
+
year = {2026},
|
| 160 |
+
eprint = {2607.09581},
|
| 161 |
+
archiveprefix = {arXiv},
|
| 162 |
+
primaryclass = {cs.CV},
|
| 163 |
+
url = {https://arxiv.org/abs/2607.09581},
|
| 164 |
+
note = {Project page: \url{https://humanaigc.github.io/wan-dancer-project/}}
|
| 165 |
}
|
| 166 |
```
|
| 167 |
|
|
|
|
| 174 |
This work builds upon and integrates components from the following open-source projects:
|
| 175 |
|
| 176 |
1. [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
|
| 177 |
+
2. [Wan2.1](https://github.com/Wan-Video/Wan2.1)
|
| 178 |
|