Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation

Jiangning Zhang, Junwei Zhu, Zhenye Gan, Donghao Luo, Chuming Lin, Feifan Xu, Xu Peng, Jianlong Hu, Yuansen Liu, Yijia Hong, Weijian Cao, Han Feng, Xu Chen, Chencan Fu, Keke He, Xiaobin Hu, Chengjie Wang

Abstract

We propose a multimodal-driven framework for high-fidelity long-term digital human animation termed $\textbf{Soul}$, which generates semantically coherent videos from a single-frame portrait image, text prompts, and audio, achieving precise lip synchronization, vivid facial expressions, and robust identity preservation. We construct Soul-1M, containing 1 million finely annotated samples with a precise automated annotation pipeline (covering portrait, upper-body, full-body, and multi-person scenes) to mitigate data scarcity, and we carefully curate Soul-Bench for comprehensive and fair evaluation of audio-/text-guided animation methods. The model is built on the Wan2.2-5B backbone, integrating audio-injection layers and multiple training strategies together with threshold-aware codebook replacement to ensure long-term generation consistency. Meanwhile, step/CFG distillation and a lightweight VAE are used to optimize inference efficiency, achieving an 11.4$\times$ speedup with negligible quality loss. Extensive experiments show that Soul significantly outperforms current leading open-source and commercial models on video quality, video-text alignment, identity preservation, and lip-synchronization accuracy, demonstrating broad applicability in real-world scenarios such as virtual anchors and film production. Project page at https://zhangzjn.github.io/projects/Soul/
BibTeX
@inproceedings{zhang2026soul,
  author = {Jiangning Zhang and Junwei Zhu and Zhenye Gan and Donghao Luo and Chuming Lin and Feifan Xu and Xu Peng and Jianlong Hu and Yuansen Liu and Yijia Hong and Weijian Cao and Han Feng and Xu Chen and Chencan Fu and Keke He and Xiaobin Hu and Chengjie Wang},
  title = {{Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2026},
  url = {https://openreview.net/forum?id=jUneqNcwXg},
}
Figure