Metraipolis › archive › dc_dafed21fc697

Wan-Animate-2: Pushing the Application Boundaries of Character Animation — arXiv:2608.06009

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06009
License (as archived)
CC0-1.0
Archived
2026-10-31T10:36:27.543Z
SHA-256 of the archived text
be0bb8ad4c621d2b0fead31ac01b5d4c6f69ea7c1d858011ec4d49f8700adcc9
Stable URL of this page
https://metraipolis.com/documento/dc_dafed21fc697

How to cite

Wan-Animate-2: Pushing the Application Boundaries of Character Animation — arXiv:2608.06009 — arXiv (en), https://arxiv.org/abs/2608.06009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dafed21fc697 (Metraipolis archive dc_dafed21fc697, sha256 be0bb8ad4c621d2b0fead31ac01b5d4c6f69ea7c1d858011ec4d49f8700adcc9)
BibTeX
@misc{dcdafed21fc697,
  title = {Wan-Animate-2: Pushing the Application Boundaries of Character Animation — arXiv:2608.06009},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06009},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dafed21fc697; sha256 be0bb8ad4c621d2b0fead31ac01b5d4c6f69ea7c1d858011ec4d49f8700adcc9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Character image animation remains a foundational yet challenging task in computer vision. Existing approaches can be broadly categorized into three paradigms: methods based on explicit motion representations suffer from extraction errors and identity drift; methods based on implicit motion features lose fine-grained dynamics through compression; and in-context learning approaches avoid intermediate representations but incur prohibitive computational costs. Furthermore, all current systems are designed for offline synthesis, unable to meet the real-time requirements of interactive applications such as digital avatars and live-streaming hosts. To address these limitations, we present Wan-Animate-2, an end-to-end character animation framework that directly consumes the driving video within a redesigned Diffusion Transformer. Our architecture achieves superior motion fidelity and identity preservation by eliminating intermediate motion extractors entirely. We further introduce text driven viewpoint control that decouples the output camera perspective from the driving video--a capability rarely supported by prior character animation methods that rely on explicit motion representations. Beyond generation quality, we present Wan-Animate-2-Lite, an efficient variant that reduces inference latency to real-time thresholds through a three-stage training paradigm: teacher forcing pretraining with error buffer mechanism, and Self-Forcing distillation with chunk-wise backpropagation. This enables streaming character animation for interactive applications, opening new deployment scenarios that were previously infeasible. Qualitative evaluations and user studies demonstrate that Wan-Animate-2 achieves high-fidelity animation results across diverse characters and motion patterns. To foster further research and community development, we will release the Wan-Animate-2-Base model weights to the public.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.06009 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T10:23:31.043Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).