Wan-Dancer

Abstract

Generating long-duration, high-definition, and rhythmically synchronized dance videos directly from music remains a significant challenge, primarily due to the temporal constraints of current diffusion models, which typically fail beyond 20 seconds. Existing approaches, whether they rely on intermediate 3D skeletons or on end-to-end video synthesis, suffer from temporal drift, identity inconsistency, and repetitive motion patterns when extended to longer horizons. To address these limitations, we propose a novel hierarchical framework for minute-scale coherent music-to-dance generation. Our method decouples the process into global keyframe planning and local temporal refinement, leveraging full-track musical context to ensure long-range coherence. Key innovations include dynamic frame rate adaptation via time-mapped RoPE embeddings for precise alignment, an optical-flow-based loss function to enhance motion continuity, and motion-speed control to preserve high-fidelity details during rapid movements. Extensive experiments demonstrate that our framework surpasses the conventional duration barrier, generating stable, 720p/30fps videos exceeding one minute with superior temporal stability. Furthermore, the model exhibits robust versatility across five distinct dance genres, conditioned on both audio and textual prompts, establishing a new state-of-the-art in coherent, long-form dance video synthesis.

BibTeX


@article{wan-dancer-2026,
  title={Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation},
  author={Mingyang Huang, Peng Zhang, Li Hu, Guangyuan Wang, Bang Zhang},
  website={https://humanaigc.github.io/wan-dancer/},
  url={https://arxiv.org/abs/2607.09581},
  year={2026}
}

Ethics Concerns

The images and music used here are for demonstrating our research capabilities and are gathered from public sources or generated by AI models. If you are a copyright holder and have concerns, please reach out to us, and we will duly remove the content.

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

Abstract

Results

1 Different Dance Genres

1.1 Chinese Classical Dance

1.2 K-pop Dance

1.3 Street Dance

1.4 Tap Dance

1.5 Latin Dance

2 Minute-scale Music-to-Dance Video Generation

3 Customized Music-to-Dance Video Generation

3.1 Single Music, Multiple References

3.2 Single Reference, Multiple Music

4 Diversity

4.1 Single Reference, Multiple Music

4.2 Single Music, Multiple References

4.3 Single Music, Single Reference

5 Creative Keyframe Applications

5.1 Outfit Change

5.2 Movements Control

6 Comparison with the SOTAs

6.1 Comparison with X-Dancer

BibTeX

Ethics Concerns