Wan-Animate-2: Pushing the Application Boundaries of Character Animation
- Published
- Source
- arXiv
- Paper number
- 841
- Field
- Computer Vision
- arXiv ID
- 2608.06009
Key points
- It removes the intermediate motion extractor, such as skeleton or SMPL, and feeds the driving video directly into the DiT.
- A dual-branch design, temporal-alignment RoPE, and sparse reference attention balance fidelity and efficiency.
- It introduces Viewpoint LoRA, which controls the output camera viewpoint from a text prompt.
- Wan-Animate-2-Lite reaches 24 fps in real time through a three-stage training process of teacher forcing, error buffer, and self-forcing.
- In user studies, it is rated equal to or better than commercial closed-source systems such as Dreamina and Kling.
Paper links
External research summaries. These are not HDATF publications or measured product results.