Wan-Dancer-14B

💜 Project &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ GitHub &nbsp&nbsp | &nbsp&nbsp🤖 MS Space&nbsp&nbsp | &nbsp&nbsp🤖 MS Model&nbsp&nbsp | &nbsp&nbsp🤗 HF Model&nbsp&nbsp | &nbsp&nbsp 📑 Paper &nbsp&nbsp

Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation

🔥 Latest News!!

• July 13, 2026: 💃 We introduce 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 and inference code. And now you can try it on ModelScope Studio or HuggingFace Space!

📑 Todo List

• Wan-Dancer Music-to-Dance
• [x] Inference code of Wan-Dancer
• [x] Checkpoints of Wan-Dancer
• [x] ComfyUI integration

Run Wan-Dancer

Installation

Clone the repo:

git clone https://github.com/Wan-Video/Wan-Dancer.git
cd Wan-Dancer

Install dependencies:

python -m venv venv_wan_dancer
source venv_wan_dancer/bin/activate

# Install package in editable mode
pip install -e .

# Install additional and specific versions dependencies
pip install moviepy loguru librosa
pip install https://mirrors.aliyun.com/pytorch-wheels/cu124/torch-2.6.0+cu124-cp310-cp310-linux_x86_64.whl
pip install torchvision==0.21.0
pip install diffusers==0.34.0
pip install yunchang==0.5.0
pip install flash_attn==2.6.3
pip install xfuser==0.4.0
pip install transformers==4.46.2

Model Download

| Models | Download Links | Description |

|--------------------|---------------------------------------------------------------------------------------------------------------------------------------------|-------------|

| Wan-Dancer-14B | 🤗 Huggingface 🤖 ModelScope | Music-to-Dance | |

Download models using huggingface-cli:

pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan-Dancer-14B --local-dir ./Wan-Dancer-14B

Download models using modelscope-cli:

pip install modelscope
modelscope download Wan-AI/Wan-Dancer-14B --local_dir ./Wan-Dancer-14B

Run Wan-Dancer

Wan-Dancer can generate long-duration, high-quality, rhythmic dance videos from music with global structure and temporal continuity. Our method decouples the process into global keyframe planning and local temporal refinement, leveraging full-track musical context to ensure long-range coherence.

1. 🎬 Generate Global Keyframe Video

Run the global stage script:

cd Wan-Dancer
./gen_video_global.sh

🔧 Important Parameters

| Parameter | Description |

|------------------------|-------------|

| seed | Random seed for reproducibility. |

| image_path | Path to reference image. Example: gen_video/ref_image/1001.jpg |

| prompt_path | Path to prompt file (defines dance style).

Available styles:Chinese Classic Dance: gen_video/prompt/古典舞_global.txt

K-Pop Dance: gen_video/prompt/kpop_global.txt

Street Dance: gen_video/prompt/街舞_global.txt

Tap Dance: gen_video/prompt/踢踏舞_global.txt

Latin Dance: gen_video/prompt/拉丁舞_global.txt

|

| music_path | Path to input music file. Example: gen_video/music/ChineseClassicDance.WAV |

| output_folder | Output directory for generated video. |

| timestamp | Timestamp identifier for output files. |

| num_inference_steps | Number of diffusion inference steps (e.g., 48). |

🌰 Examples

| Dance Genres | Parameter | Generated Global Video |

| ------------ |-----------------------|-----------------|

| Chinese Classical Dance | seed=0

image_path='gen_video/ref_image/1001.jpg'

prompt_path='gen_video/prompt/古典舞_global.txt'

music_path='gen_video/music/ChineseClassicDance.WAV'

num_inference_steps=48

cfg_scale=5 |  |

| Street Dance | seed=0

image_path='gen_video/ref_image/2001.jpg'

prompt_path='gen_video/prompt/街舞_global.txt'

music_path='gen_video/music/StreetDance.WAV'

num_inference_steps=48

cfg_scale=5 |  |

| K-Pop Dance | seed=0

image_path='gen_video/ref_image/3001.jpg'

prompt_path='gen_video/prompt/kpop_global.txt'

music_path='gen_video/music_suno/3001.WAV'

num_inference_steps=48

cfg_scale=5 |  |

| Latin Dance | seed=0

image_path='gen_video/ref_image/4001.jpg'

prompt_path='gen_video/prompt/拉丁舞_global.txt'

music_path='gen_video/music/LatinDance.WAV'

num_inference_steps=48

cfg_scale=5 |  |

| Tap Dance | seed=0

image_path='gen_video/ref_image/5001.jpg'

prompt_path='gen_video/prompt/踢踏舞_global.txt'

music_path='gen_video/music/TapDance.wav'

num_inference_steps=48

cfg_scale=5 | |

2. 🎥 Generate Final High-Resolution Video

Run the local refinement stage:

cd Wan-Dancer
./gen_video_local.sh

🔧 Additional Required Parameters

| Parameter | Description |

|-----------------------|-------------|

| global_video_path | Path to the global video generated in Step 1. Required for local refinement. |

| prompt_path | Path to prompt file (defines dance style).

Available styles:Chinese Classic Dance: gen_video/prompt/古典舞_local.txt

K-Pop Dance: gen_video/prompt/kpop_local.txt

Street Dance: gen_video/prompt/街舞_local.txt

Tap Dance: gen_video/prompt/踢踏舞_local.txt

Latin Dance: gen_video/prompt/拉丁舞_local.txt

|

✅ All other parameters (seed, image_path, etc.) are identical to Step 1.

🌰 Examples

| Dance Genres | Parameter | Generated Final Video |

| ------------ |-----------------------|-----------------|

| Chinese Classical Dance | seed=0

image_path='gen_video/ref_image/1001.jpg'

prompt_path='gen_video/prompt/古典舞_local.txt'

music_path='gen_video/music/ChineseClassicDance.WAV'

num_inference_steps=24

cfg_scale=5

global_video_path='outputs/global_video/1001_ChineseClassicDance_seed0.mp4' |  |

| Street Dance | seed=0

image_path='gen_video/ref_image/2001.jpg'

prompt_path='gen_video/prompt/街舞_local.txt'

music_path='gen_video/music/StreetDance.WAV'

num_inference_steps=24

cfg_scale=5

global_video_path='outputs/global_video/2001_StreetDance_seed0.mp4' |  |

| K-Pop Dance | seed=100

image_path='gen_video/ref_image/3001.jpg'

prompt_path='gen_video/prompt/kpop_local.txt'

music_path='gen_video/music_suno/3001.WAV'

num_inference_steps=24

cfg_scale=5

global_video_path='outputs/global_video/3001_KPopDance_seed0.mp4' |  |

| Latin Dance | seed=0

image_path='gen_video/ref_image/4001.jpg'

prompt_path='gen_video/prompt/拉丁舞_local.txt'

music_path='gen_video/music/LatinDance.WAV'

num_inference_steps=24

cfg_scale=5

global_video_path='outputs/global_video/4001_LatinDance_seed0.mp4' |  |

| Tap Dance | seed=0

image_path='gen_video/ref_image/5001.jpg'

prompt_path='gen_video/prompt/踢踏舞_local.txt'

music_path='gen_video/music/TapDance.wav'

num_inference_steps=24

cfg_scale=5

global_video_path='outputs/global_video/5001_TapDance_seed0.mp4' |  |

Note: The num_inference_steps should be set to a larger value (e.g., 48) for longer time videos.

-------

Citation

If you use this code or framework in your research, please cite:

@article{wan-dancer-2026,
  title         = {Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation},
  author        = {Huang, Mingyang and Zhang, Peng and Hu, Li and Wang, Guangyuan and Zhang, Ruoshi and Lu, Yi and Cheng, Gang and Zhang, Bang},
  year          = {2026},
  eprint        = {2607.09581},
  archiveprefix = {arXiv},
  primaryclass  = {cs.CV},
  url           = {https://arxiv.org/abs/2607.09581},
  note          = {Project page: \url{https://humanaigc.github.io/wan-dancer-project/}}
}

License Agreement

This project is licensed under the Apache 2.0 License — see the LICENSE file for details.

Acknowledgements

This work builds upon and integrates components from the following open-source projects:

1. DiffSynth-Studio

2. Wan2.1