Search papers, labs, and topics across Lattice.
This paper introduces EditaLive, a real-time character video editing framework specifically designed for live streaming, addressing the limitations of conventional scene-level editing methods that struggle with human-centric content. By leveraging a pretrained image animation model and adapting it for causal streaming generation, EditaLive achieves high-quality video editing while maintaining facial expression consistency and minimizing latency. Extensive experiments show that EditaLive outperforms existing methods, providing a seamless editing experience suitable for interactive environments.
EditaLive achieves real-time character video editing with state-of-the-art performance, preserving facial expressions while eliminating latency issues in live streaming.
Conventional video editing primarily focuses on scene-level content, whereas live streaming places greater emphasis on the human subject. However, directly applying existing video-editing methods to human-centric live streaming remains challenging, as they may introduce facial-expression inconsistencies and typically depend on multiple offline inference steps, making them unsuitable for real-time interaction. We propose EditaLive, a novel framework for real-time streaming character video editing. In detail, 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. Besides, we adapt the model from offline bidirectional to causal streaming generation, and design an aligned self-rollout distillation strategy that compresses the model into a two-step sampler, where fixed RoPE and align forcing reduce training--inference discrepancies, and first-frame preserved sparse attention filters redundant historical information to mitigate appearance drift. Extensive experiments demonstrate that EditaLive delivers state-of-the-art editing performance with faithful preservation of facial expressions and low-latency real-time streaming inference.
