Meet Soap2Soap — Video-to-Video generation via multi-agent collaboration.</p>\n<p>Transform any video into a fully stylized animated version — Pixar, Disney, LEGO, anime, clay, and more — with consistent characters, environments, and cinematic composition preserved across every shot.</p>\n","updatedAt":"2026-05-26T01:08:48.034Z","author":{"_id":"64440be5af034cdfd69ca3a7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64440be5af034cdfd69ca3a7/qmx24QiDFT29vleCxL9TX.jpeg","fullname":"Qinghong (Kevin) Lin","name":"KevinQHLin","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":46,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8257251977920532},"editors":["KevinQHLin"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64440be5af034cdfd69ca3a7/qmx24QiDFT29vleCxL9TX.jpeg"],"reactions":[],"isReport":false}},{"id":"6a1654a91ddb71b163e9f6eb","author":{"_id":"64440be5af034cdfd69ca3a7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64440be5af034cdfd69ca3a7/qmx24QiDFT29vleCxL9TX.jpeg","fullname":"Qinghong (Kevin) Lin","name":"KevinQHLin","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":46,"isUserFollowing":false},"createdAt":"2026-05-27T02:19:21.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","html":"<p>Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration</p>\n","updatedAt":"2026-05-27T02:19:21.011Z","author":{"_id":"64440be5af034cdfd69ca3a7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64440be5af034cdfd69ca3a7/qmx24QiDFT29vleCxL9TX.jpeg","fullname":"Qinghong (Kevin) Lin","name":"KevinQHLin","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":46,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6175588965415955},"editors":["KevinQHLin"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64440be5af034cdfd69ca3a7/qmx24QiDFT29vleCxL9TX.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.17423","authors":[{"_id":"6a14f1bcb57a1823d5708997","name":"Yiren Song","hidden":false},{"_id":"6a14f1bcb57a1823d5708998","name":"Huilin Zhong","hidden":false},{"_id":"6a14f1bcb57a1823d5708999","name":"Kevin Qinghong Lin","hidden":false},{"_id":"6a14f1bcb57a1823d570899a","name":"Haofan Wang","hidden":false},{"_id":"6a14f1bcb57a1823d570899b","name":"Mike Zheng Shou","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/64440be5af034cdfd69ca3a7/Ixisl8uY4NUeTgZdFMSQj.mp4"],"publishedAt":"2026-05-17T00:00:00.000Z","submittedOnDailyAt":"2026-05-27T00:00:00.000Z","title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","submittedOnDailyBy":{"_id":"64440be5af034cdfd69ca3a7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64440be5af034cdfd69ca3a7/qmx24QiDFT29vleCxL9TX.jpeg","isPro":false,"fullname":"Qinghong (Kevin) Lin","user":"KevinQHLin","type":"user","name":"KevinQHLin"},"summary":"We study series-level cinematic remaking, a long-horizon video-to-video generation problem that localizes full episodes or films via stylization or actor replacement while strictly preserving narrative structure, motion choreography, and character identity across hundreds of shots. Existing video generation and editing pipelines often break down in this regime due to compounding identity drift, background mutation, and semantic erosion under large camera motions and viewpoint changes. We propose Soap2Soap, a multi-agent framework that enforces long-term language-visual consistency through a Dual-Bridge Consistency mechanism: a scene-aware JSON screenplay serving as a persistent semantic backbone, and dynamically allocated visual reference anchors at both scene and shot levels. To suppress drift before video synthesis, we introduce batch keyframe consistency, jointly generating multiple keyframes in a shared latent context via a grid-based formulation. A closed-loop verification agent further audits identity, stability, and alignment to trigger selective regeneration. Experiments on SoapBench demonstrate strong improvements over commercial video generation APIs in long-term consistency and narrative fidelity.","upvotes":14,"discussionId":"6a14f1bdb57a1823d570899c","githubRepo":"https://github.com/showlab/Soap2Soap","githubRepoAddedBy":"user","ai_summary":"A multi-agent framework called Soap2Soap is presented for long-horizon video-to-video generation that maintains narrative structure and character identity across extended sequences through consistent semantic backbone and visual reference anchors.","ai_keywords":["video-to-video generation","cinematic remaking","narrative structure","identity drift","background mutation","semantic erosion","multi-agent framework","Dual-Bridge Consistency","JSON screenplay","visual reference anchors","keyframe consistency","latent context","closed-loop verification","SoapBench"],"githubStars":31,"organization":{"_id":"63a553c4ce5763e06f78669c","name":"showlab","fullname":"Show Lab","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1671779505215-63a55320ce5763e06f78519c.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65519eb532f278f503b3b2c3","avatarUrl":"/avatars/2e180f7b20189cd2d8a75e05c2913c5d.svg","isPro":false,"fullname":"QuanjianSong","user":"QuanjianSong","type":"user"},{"_id":"633407947eb49986ce070a6c","avatarUrl":"/avatars/84245495d36f605a900950a3a76d4386.svg","isPro":false,"fullname":"song yiren","user":"songyiren","type":"user"},{"_id":"64440be5af034cdfd69ca3a7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64440be5af034cdfd69ca3a7/qmx24QiDFT29vleCxL9TX.jpeg","isPro":false,"fullname":"Qinghong (Kevin) Lin","user":"KevinQHLin","type":"user"},{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"},{"_id":"65d9be67be18bfea69c63830","avatarUrl":"/avatars/fe68775d214b76f8812db0d066d5be63.svg","isPro":false,"fullname":"Jialong Sun","user":"Pillow-1","type":"user"},{"_id":"67e9fc3797cd6860c81d5838","avatarUrl":"/avatars/6c37731156bf52c123bd390823890d28.svg","isPro":false,"fullname":"Jangho Park","user":"jhpark96","type":"user"},{"_id":"6411c801e872ae3fb1e2c96e","avatarUrl":"/avatars/f8898dc13d700e545eedbbfab1c18353.svg","isPro":true,"fullname":"Franklin","user":"Franklinzhang","type":"user"},{"_id":"637f114c1dbae0919108987d","avatarUrl":"/avatars/23d73811b697261ceb80ef1b0806a633.svg","isPro":false,"fullname":"Zizhao Tong","user":"zizhaotong","type":"user"},{"_id":"6836a5aa14ebb7ff0c031871","avatarUrl":"/avatars/8bb04314e9b1cb3927b159f511796703.svg","isPro":false,"fullname":"Yang Pei","user":"yangpei-comp","type":"user"},{"_id":"623461fccd8a0462e55b3666","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1647600114080-noauth.jpeg","isPro":true,"fullname":"Guian Fang","user":"Enderfga","type":"user"},{"_id":"636b3f9ce3ad78bc68b67541","avatarUrl":"/avatars/2b7e745953ae39e01222e99fb63b279e.svg","isPro":false,"fullname":"yuxuan","user":"zzyx","type":"user"},{"_id":"68ea15e4d7b8e72eb586c1f9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/tRzkH43YZiPs3pIgUCWVd.png","isPro":false,"fullname":"Huilin Zhong","user":"ZhongLv","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"63a553c4ce5763e06f78669c","name":"showlab","fullname":"Show Lab","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1671779505215-63a55320ce5763e06f78519c.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.17423.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2605.17423 in a model README.md to link it from this page.

Cite arxiv.org/abs/2605.17423 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2605.17423 in a Space README.md to link it from this page.