<video src=\"https://cdn-uploads.huggingface.co/production/uploads/63184c517ca1b876d99b7e0e/emAXUD2-OAUt_T9mgEov3.mp4\" controls=\"\" class=\"max-w-full!\"></video></p>","updatedAt":"2026-08-28T12:49:35.165Z","author":{"_id":"63184c517ca1b876d99b7e0e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63184c517ca1b876d99b7e0e/b-qDExoeJuDXK0cJBZKnz.jpeg","fullname":"Xiaodong Cun","name":"vinthony","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":344,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5204703211784363},"editors":["vinthony"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/63184c517ca1b876d99b7e0e/b-qDExoeJuDXK0cJBZKnz.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.27123","authors":[{"_id":"6a90ecfaa64059bab69c35a7","name":"Zhiyuan Li","hidden":false},{"_id":"6a90ecfaa64059bab69c35a8","name":"Chi-Man Pun","hidden":false},{"_id":"6a90ecfaa64059bab69c35a9","name":"Peng-Tao Jiang","hidden":false},{"_id":"6a90ecfaa64059bab69c35aa","name":"Bo Li","hidden":false},{"_id":"6a90ecfaa64059bab69c35ab","name":"Xiaodong Cun","hidden":false}],"publishedAt":"2026-08-27T00:00:00.000Z","submittedOnDailyAt":"2026-08-28T00:00:00.000Z","title":"EditaLive! Unified Character Video Editing for Live Streaming","submittedOnDailyBy":{"_id":"63184c517ca1b876d99b7e0e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63184c517ca1b876d99b7e0e/b-qDExoeJuDXK0cJBZKnz.jpeg","isPro":false,"fullname":"Xiaodong Cun","user":"vinthony","type":"user","name":"vinthony"},"summary":"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.","upvotes":2,"discussionId":"6a90ecfaa64059bab69c35ac","projectPage":"https://huai-chang.github.io/EditaLive/","githubRepo":"https://github.com/GVCLab/EditaLive","githubRepoAddedBy":"user","ai_summary":"EditaLive enables real-time human-centric live-stream video editing by adapting an image animation model to causal streaming generation with distilled two-step sampling and sparse attention.","ai_keywords":["image animation model","Wan-Animate","instruction-based video editing","CharEdit-50K","causal streaming generation","self-rollout distillation","two-step sampler","RoPE","sparse attention","appearance drift"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":6,"organization":{"_id":"69402e7fa7c562569cd809c2","name":"GVCLab","fullname":"GVC Lab at Great Bay University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/63184c517ca1b876d99b7e0e/0mQ2Re10Y0HKnD878FGiU.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63184c517ca1b876d99b7e0e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63184c517ca1b876d99b7e0e/b-qDExoeJuDXK0cJBZKnz.jpeg","isPro":false,"fullname":"Xiaodong Cun","user":"vinthony","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"69402e7fa7c562569cd809c2","name":"GVCLab","fullname":"GVC Lab at Great Bay University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/63184c517ca1b876d99b7e0e/0mQ2Re10Y0HKnD878FGiU.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.27123.md","query":{}}">
EditaLive! Unified Character Video Editing for Live Streaming
Abstract
EditaLive enables real-time human-centric live-stream video editing by adapting an image animation model to causal streaming generation with distilled two-step sampling and sparse attention.
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.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2608.27123 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.27123 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.27123 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.