EditaLive! Unified Character Video Editing for Live Streaming

TL;DR - EditaLive is a framework for instruction-driven, real-time character video editing in live streams. It adapts an image-animation model for causal streaming and preserves facial expressions while reducing inference to a low-latency two-step process.

• Repurposes Wan-Animate by leveraging its separation of character appearance and motion.
• Uses the CharEdit-50K dataset to train reference-frame editing and video reconstruction.
• Converts offline bidirectional generation into causal streaming generation.
• Combines aligned self-rollout distillation, fixed RoPE, align forcing, and sparse attention to reduce latency and appearance drift.