🛰️ Daily AI Frontier
‹ back to 2026-08-30

EditaLive! Unified Character Video Editing for Live Streaming

Research Multimodal & Generative

Ranking

Overall 80
Content 85
Popularity 69

Observed public metrics from 1 member.

Merged summary

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.

Sources (1)

EditaLive! Unified Character Video Editing for Live Streaming

arXiv cs.CV Zhiyuan Li, Chi-Man Pun, Peng-Tao Jiang, Bo Li, Xiaodong Cun 2026-08-27 arXiv:2608.27123
Public signals Hugging Face upvotes 5
Providers: Hugging Face · Upvotes 5 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-25 14:26:00.840450 UTC

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.
item →