A pretrained image animation model that naturally decouples appearance from motion can be repurposed as a base model for instruction-based human-centric video editing

we start from a pretrained image animation model (Wan-Animate), which naturally decouples appearance from motion, and repurpose it as the base model for instruction-based human-centric video editing by reference frame editing and video reconstruction via the collected CharEdit-50K dataset

http://arxiv.org/abs/2608.27123v1