Model reference · open weights
Wan-Dancer is an open-weight video model from Wan-AI, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Wan-Dancer-14B 💜 <a href="https://humanaigc.github.io/wan-dancer-project/"<bProject</b</a    ｜    🖥️ <a href="https://github.com/Wan-Video/Wan-Dancer"GitHub</a    |   🤖 <a href="https://modelscope.ai/studios/Wan-AI/Wan-Dancer"MS Space</a   |   🤖 <a href="https://www.modelscope.cn/models/Wan-AI/Wan-Dancer-14B"MS Model</a   |   🤗 <a href="https://huggingface.co/Wan-AI/Wan-Dancer-14B"HF Model</a   |    📑 <a href="https://arxiv.org/abs/2607.09581"Paper</a    Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation <be 🔥 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: Install dependencies: Model Download Download models using huggingface-cli: Download models using modelscope-cli: 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: 🔧 Important Parameters 🌰 Examples 2. 🎥 Generate Final High-Resolution Video Run the local refinement stage: 🔧 Additional Required Parameters ✅ All other parameters (seed, imagepath, etc.) are identical to Step 1. 🌰 Examples Citation If you use this code or framework in your research, please cite: 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
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Wan-AI |
|---|---|
| Type | Video models |
| Variants | 1 |
| Runs with | diffusers |
| Released | 2026-07-10 |
| Popularity | 6k downloads / month |
| Likes | 183 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Wan-Dancer-14B | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys wan-dancer for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wan-dancer below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/videos/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"wan-dancer","prompt":"a drone shot over a forest"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore