Hugging Face Daily Papers · July 10, 2026 · 3 min read

Vidu S1: A Real-Time Interactive Video Generation Model

#model-release #voice #video-gen #paper #gpu

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Like Read original ↗

Highly recommend giving Vidu S1 a try~\n<ul>\n<li>User Guide: <a href=\"https://auspicious-passive-36a.notion.site/Vidu-S1-Introduction-34324005a3e48009b3f3d9c07c79d83b\" rel=\"nofollow\">https://auspicious-passive-36a.notion.site/Vidu-S1-Introduction-34324005a3e48009b3f3d9c07c79d83b</a>\n</li>\n<li>Try it now: <a href=\"https://www.vidu.com/vidu-stream\" rel=\"nofollow\">https://www.vidu.com/vidu-stream</a>\n</li>\n<li>API Platform: <a href=\"https://platform.vidu.com/live/landing\" rel=\"nofollow\">https://platform.vidu.com/live/landing</a>\n</li>\n<li>Paper: <a href=\"https://arxiv.org/pdf/2607.03118\" rel=\"nofollow\">https://arxiv.org/pdf/2607.03118</a>\n</li>\n<li>Github: <a href=\"https://github.com/shengshu-ai/Vidu-S1\" rel=\"nofollow\">https://github.com/shengshu-ai/Vidu-S1</a>\n</li>\n</ul>\n","updatedAt":"2026-07-10T02:59:12.042Z","author":{"_id":"66c0a08bac74db25de8427ec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66c0a08bac74db25de8427ec/9D-piDBZqSt6KNkHImmkv.jpeg","fullname":"Jintao Zhang","name":"jt-zhang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":56,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.3817668855190277},"editors":["jt-zhang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/66c0a08bac74db25de8427ec/9D-piDBZqSt6KNkHImmkv.jpeg"],"reactions":[{"reaction":"🔥","users":["jt-zhang","huang2007","Jungang","thinkeccencer"],"count":4},{"reaction":"❤️","users":["jt-zhang","huang2007","Jungang","thinkeccencer"],"count":4}],"isReport":false}},{"id":"6a507070da26218515929aa0","author":{"_id":"66c0a08bac74db25de8427ec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66c0a08bac74db25de8427ec/9D-piDBZqSt6KNkHImmkv.jpeg","fullname":"Jintao Zhang","name":"jt-zhang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":56,"isUserFollowing":false},"createdAt":"2026-07-10T04:09:20.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Vidu S1 强烈建议试玩一下~\n\n- 使用说明：https://shengshu.feishu.cn/wiki/PSlDwao9GiEGOKkWS2FcWRtOnwe\n\n- 立即体验：https://www.vidu.cn/vidu-stream\n\n- API 开放平台：https://platform.vidu.com/live/landing\n\n- Paper: https://arxiv.org/pdf/2607.03118\n\n- Github: https://github.com/shengshu-ai/Vidu-S1","html":"Vidu S1 强烈建议试玩一下~\n<ul>\n<li>使用说明：<a href=\"https://shengshu.feishu.cn/wiki/PSlDwao9GiEGOKkWS2FcWRtOnwe\" rel=\"nofollow\">https://shengshu.feishu.cn/wiki/PSlDwao9GiEGOKkWS2FcWRtOnwe</a>\n</li>\n<li>立即体验：<a href=\"https://www.vidu.cn/vidu-stream\" rel=\"nofollow\">https://www.vidu.cn/vidu-stream</a>\n</li>\n<li>API 开放平台：<a href=\"https://platform.vidu.com/live/landing\" rel=\"nofollow\">https://platform.vidu.com/live/landing</a>\n</li>\n<li>Paper: <a href=\"https://arxiv.org/pdf/2607.03118\" rel=\"nofollow\">https://arxiv.org/pdf/2607.03118</a>\n</li>\n<li>Github: <a href=\"https://github.com/shengshu-ai/Vidu-S1\" rel=\"nofollow\">https://github.com/shengshu-ai/Vidu-S1</a>\n</li>\n</ul>\n","updatedAt":"2026-07-10T04:09:20.343Z","author":{"_id":"66c0a08bac74db25de8427ec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66c0a08bac74db25de8427ec/9D-piDBZqSt6KNkHImmkv.jpeg","fullname":"Jintao Zhang","name":"jt-zhang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":56,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"zh","probability":0.514350950717926},"editors":["jt-zhang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/66c0a08bac74db25de8427ec/9D-piDBZqSt6KNkHImmkv.jpeg"],"reactions":[{"reaction":"👀","users":["jt-zhang","Jungang"],"count":2}],"isReport":false}},{"id":"6a508dec6286e005d478810b","author":{"_id":"67f35b359d88f81cc69a17c0","avatarUrl":"/avatars/96ece83186f40db7d13010b26b6c1c17.svg","fullname":"thinkessence","name":"thinkeccencer","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2026-07-10T06:15:08.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"amazing！","html":"amazing！\n","updatedAt":"2026-07-10T06:15:08.241Z","author":{"_id":"67f35b359d88f81cc69a17c0","avatarUrl":"/avatars/96ece83186f40db7d13010b26b6c1c17.svg","fullname":"thinkessence","name":"thinkeccencer","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"zh","probability":0.8385421633720398},"editors":["thinkeccencer"],"editorAvatarUrls":["/avatars/96ece83186f40db7d13010b26b6c1c17.svg"],"reactions":[],"isReport":false}},{"id":"6a508f23678368ce3d6025f0","author":{"_id":"60c94c629cacafb192d805fc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c94c629cacafb192d805fc/nA0jBaVl7Ti5LGoZ2myAs.png","fullname":"TimeLordRaps","name":"TimeLordRaps","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12,"isUserFollowing":false},"createdAt":"2026-07-10T06:20:19.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","hiddenReason":"Spam","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2026-07-10T12:32:32.746Z","author":{"_id":"60c94c629cacafb192d805fc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c94c629cacafb192d805fc/nA0jBaVl7Ti5LGoZ2myAs.png","fullname":"TimeLordRaps","name":"TimeLordRaps","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12,"isUserFollowing":false}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}},{"id":"6a508f856ab7e40002721d62","author":{"_id":"60c94c629cacafb192d805fc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c94c629cacafb192d805fc/nA0jBaVl7Ti5LGoZ2myAs.png","fullname":"TimeLordRaps","name":"TimeLordRaps","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12,"isUserFollowing":false},"createdAt":"2026-07-10T06:21:57.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","hiddenReason":"Abuse","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2026-07-10T12:32:15.567Z","author":{"_id":"60c94c629cacafb192d805fc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c94c629cacafb192d805fc/nA0jBaVl7Ti5LGoZ2myAs.png","fullname":"TimeLordRaps","name":"TimeLordRaps","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12,"isUserFollowing":false}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}},{"id":"6a508fb690dd5bd7c41f3ba3","author":{"_id":"60c94c629cacafb192d805fc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c94c629cacafb192d805fc/nA0jBaVl7Ti5LGoZ2myAs.png","fullname":"TimeLordRaps","name":"TimeLordRaps","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12,"isUserFollowing":false},"createdAt":"2026-07-10T06:22:46.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","hiddenReason":"Abuse","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2026-07-10T12:32:19.945Z","author":{"_id":"60c94c629cacafb192d805fc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c94c629cacafb192d805fc/nA0jBaVl7Ti5LGoZ2myAs.png","fullname":"TimeLordRaps","name":"TimeLordRaps","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12,"isUserFollowing":false}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.03118","authors":[{"_id":"6a505b7675fd3d966bd45d93","user":{"_id":"66c0a08bac74db25de8427ec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66c0a08bac74db25de8427ec/9D-piDBZqSt6KNkHImmkv.jpeg","isPro":false,"fullname":"Jintao Zhang","user":"jt-zhang","type":"user","name":"jt-zhang"},"name":"Jintao Zhang","status":"claimed_verified","statusLastChangedAt":"2026-07-10T07:45:02.035Z","hidden":false},{"_id":"6a505b7675fd3d966bd45d94","name":"Kai Jiang","hidden":false},{"_id":"6a505b7675fd3d966bd45d95","name":"Jintao Chen","hidden":false},{"_id":"6a505b7675fd3d966bd45d96","name":"Xu Wang","hidden":false},{"_id":"6a505b7675fd3d966bd45d97","name":"Yang Luo","hidden":false},{"_id":"6a505b7675fd3d966bd45d98","name":"Yuji Wang","hidden":false},{"_id":"6a505b7675fd3d966bd45d99","name":"Dechuang Chen","hidden":false},{"_id":"6a505b7675fd3d966bd45d9a","user":{"_id":"64b76528fdb702b3d8641514","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b76528fdb702b3d8641514/Ho-uWcQCAEIURM1lhWEWJ.jpeg","isPro":false,"fullname":"Jungang Li","user":"Jungang","type":"user","name":"Jungang"},"name":"Jungang Li","status":"claimed_verified","statusLastChangedAt":"2026-07-10T07:44:54.616Z","hidden":false},{"_id":"6a505b7675fd3d966bd45d9b","name":"Chengyang Ye","hidden":false},{"_id":"6a505b7675fd3d966bd45d9c","name":"Marco Chen","hidden":false},{"_id":"6a505b7675fd3d966bd45d9d","user":{"_id":"64c269a52d73768f07ac266c","avatarUrl":"/avatars/d497a960f8aef6a974907b68ed750c1c.svg","isPro":true,"fullname":"Zhu Hongzhou","user":"zhuhz22","type":"user","name":"zhuhz22"},"name":"Hongzhou Zhu","status":"claimed_verified","statusLastChangedAt":"2026-07-10T07:44:59.447Z","hidden":false},{"_id":"6a505b7675fd3d966bd45d9e","name":"Min Zhao","hidden":false},{"_id":"6a505b7675fd3d966bd45d9f","name":"Yuxuan Jiang","hidden":false},{"_id":"6a505b7675fd3d966bd45da0","name":"Zhengkun Huang","hidden":false},{"_id":"6a505b7675fd3d966bd45da1","name":"Chendong Xiang","hidden":false},{"_id":"6a505b7675fd3d966bd45da2","name":"Kaiwen Zheng","hidden":false},{"_id":"6a505b7675fd3d966bd45da3","name":"Haoxu Wang","hidden":false},{"_id":"6a505b7675fd3d966bd45da4","name":"Xiaohang Wang","hidden":false},{"_id":"6a505b7675fd3d966bd45da5","user":{"_id":"646ecab85d05113e43280e75","avatarUrl":"/avatars/8d123a17b8ad528029bc33d01dbcb532.svg","isPro":false,"fullname":"Qi Jia","user":"kuafou","type":"user","name":"kuafou"},"name":"Qi Jia","status":"claimed_verified","statusLastChangedAt":"2026-07-10T07:44:56.955Z","hidden":false},{"_id":"6a505b7675fd3d966bd45da6","name":"Xin Chen","hidden":false},{"_id":"6a505b7675fd3d966bd45da7","name":"Yimin Chen","hidden":false},{"_id":"6a505b7675fd3d966bd45da8","name":"Youhe Jiang","hidden":false},{"_id":"6a505b7675fd3d966bd45da9","name":"Fangcheng Fu","hidden":false},{"_id":"6a505b7675fd3d966bd45daa","name":"Zhijie Deng","hidden":false},{"_id":"6a505b7675fd3d966bd45dab","name":"Fan Bao","hidden":false},{"_id":"6a505b7675fd3d966bd45dac","name":"Jianfei Chen","hidden":false},{"_id":"6a505b7675fd3d966bd45dad","name":"Jun Zhu","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/66c0a08bac74db25de8427ec/tOyCS73TCOOklV-7xys8i.png"],"publishedAt":"2026-07-03T00:00:00.000Z","submittedOnDailyAt":"2026-07-10T00:00:00.000Z","title":"Vidu S1: A Real-Time Interactive Video Generation Model","submittedOnDailyBy":{"_id":"66c0a08bac74db25de8427ec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66c0a08bac74db25de8427ec/9D-piDBZqSt6KNkHImmkv.jpeg","isPro":false,"fullname":"Jintao Zhang","user":"jt-zhang","type":"user","name":"jt-zhang"},"summary":"We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the best performance across all test metrics while fully meeting real-time inference requirements. A playable online demo is available at https://vidu.com/vidu-stream.","upvotes":108,"discussionId":"6a505b7675fd3d966bd45dae","projectPage":"https://vidu.com/vidu-stream","githubRepo":"https://github.com/shengshu-ai/Vidu-S1","githubRepoAddedBy":"user","ai_summary":"Vidu S1 is a real-time interactive video generation model that supports voice-controlled digital character animation with infinite-length output and high frame rate on consumer hardware.","ai_keywords":["TurboDiffusion","TurboServe","real-time video generation","voice control","digital characters","infinite-length video","frame rate","consumer GPUs"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":127,"organization":{"_id":"628735cbc83a2d6ab8d14a66","name":"Tsinghua","fullname":"Tsinghua University","avatar":"https://www.gravatar.com/avatar/6c5c1441e3283e7543342e59277ea219?d=retro&size=100"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"66c0a08bac74db25de8427ec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66c0a08bac74db25de8427ec/9D-piDBZqSt6KNkHImmkv.jpeg","isPro":false,"fullname":"Jintao Zhang","user":"jt-zhang","type":"user"},{"_id":"67b6eda5553eedaabedc9d5f","avatarUrl":"/avatars/857d2f01e714fd7bfb348873fe259c8a.svg","isPro":true,"fullname":"Yuji Wang","user":"yujiwang0606","type":"user"},{"_id":"66a0cb038668e1386938a9b1","avatarUrl":"/avatars/804c69397cb7351b47bfcc962da9cb0d.svg","isPro":false,"fullname":"Yuxuan Jiang","user":"YuXuAN0622","type":"user"},{"_id":"6a4c752183b91c59e4408ffc","avatarUrl":"/avatars/f5a8f4a4fafd94aa9a5be13bdf30b0f8.svg","isPro":false,"fullname":"zzz","user":"concerto4","type":"user"},{"_id":"654cdf9895edd6dffccdcf65","avatarUrl":"/avatars/1e3ae4c096092388b2c7d0bc42869c9d.svg","isPro":false,"fullname":"Zhaoyan Sun","user":"curtis-sun","type":"user"},{"_id":"652bf7edc3cba555d5673c6e","avatarUrl":"/avatars/78f6416c30203b30671f8423f061c657.svg","isPro":true,"fullname":"Kaiwen Zheng","user":"worstcoder","type":"user"},{"_id":"64f409e314d3972955dfb8a6","avatarUrl":"/avatars/bedc8ad492b1a0034e3c81b43670834c.svg","isPro":true,"fullname":"Yang Luo","user":"yang29","type":"user"},{"_id":"646ecab85d05113e43280e75","avatarUrl":"/avatars/8d123a17b8ad528029bc33d01dbcb532.svg","isPro":false,"fullname":"Qi Jia","user":"kuafou","type":"user"},{"_id":"6880596eda3898bbaa326b02","avatarUrl":"/avatars/7cfcd158f7000ba4cd0b43023df21ba9.svg","isPro":false,"fullname":"lei ma","user":"ma1127","type":"user"},{"_id":"66c0167ba474a917fcc27951","avatarUrl":"/avatars/297e6c4041ac31098d9d4d02f156134a.svg","isPro":false,"fullname":"Yuyang Gao","user":"GYYG111","type":"user"},{"_id":"6451275d6db3be7ee57a7108","avatarUrl":"/avatars/a77d8732b7a8413b84ca4b1f04a0ab71.svg","isPro":false,"fullname":"HD","user":"Dtech21","type":"user"},{"_id":"6270324ebecab9e2dcf245de","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6270324ebecab9e2dcf245de/cMbtWSasyNlYc9hvsEEzt.jpeg","isPro":false,"fullname":"Kye Gomez","user":"kye","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":1,"organization":{"_id":"628735cbc83a2d6ab8d14a66","name":"Tsinghua","fullname":"Tsinghua University","avatar":"https://www.gravatar.com/avatar/6c5c1441e3283e7543342e59277ea219?d=retro&size=100"},"query":{}}">

Papers

arxiv:2607.03118

Vidu S1: A Real-Time Interactive Video Generation Model

Published on Jul 3

· Submitted by

Jintao Zhang on Jul 10

Authors:

Jintao Zhang ,

Jungang Li ,

Hongzhou Zhu ,

Qi Jia ,

Abstract

Vidu S1 is a real-time interactive video generation model that supports voice-controlled digital character animation with infinite-length output and high frame rate on consumer hardware.

Generated by Qwen/Qwen2.5-Coder-32B-Instruct

We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the best performance across all test metrics while fully meeting real-time inference requirements. A playable online demo is available at https://vidu.com/vidu-stream.