WithEveryone generates coherent group images from five to ten reference identities</p>\n","updatedAt":"2026-08-21T02:02:05.920Z","author":{"_id":"634bde123d11eaedd889e277","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1665916392312-noauth.png","fullname":"Hengyuan Xu","name":"DobyXu","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.760926365852356},"editors":["DobyXu"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1665916392312-noauth.png"],"reactions":[{"reaction":"🔥","users":["wchengad"],"count":1}],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.20336","authors":[{"_id":"6a87af9a89e517cbfd75dbb9","name":"Hengyuan Xu","hidden":false},{"_id":"6a87af9a89e517cbfd75dbba","name":"Qixun Wang","hidden":false},{"_id":"6a87af9a89e517cbfd75dbbb","name":"Yiji Cheng","hidden":false},{"_id":"6a87af9a89e517cbfd75dbbc","name":"Miles Yang","hidden":false},{"_id":"6a87af9a89e517cbfd75dbbd","name":"Zhao Zhong","hidden":false},{"_id":"6a87af9a89e517cbfd75dbbe","name":"Wei Cheng","hidden":false},{"_id":"6a87af9a89e517cbfd75dbbf","name":"Xingjun Ma","hidden":false},{"_id":"6a87af9a89e517cbfd75dbc0","name":"Yu-gang Jiang","hidden":false}],"publishedAt":"2026-08-20T00:00:00.000Z","submittedOnDailyAt":"2026-08-21T00:00:00.000Z","title":"WithEveryone: Unified Planning and Identity Grounding for Group Image Generation","submittedOnDailyBy":{"_id":"634bde123d11eaedd889e277","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1665916392312-noauth.png","isPro":false,"fullname":"Hengyuan Xu","user":"DobyXu","type":"user","name":"DobyXu"},"summary":"Identity-preserving image generation becomes increasingly unreliable when a scene must contain many specified people. Beyond retaining each identity, the model must bind every reference to a distinct person and location, while training-time identity losses must establish correspondence among several noisy predicted faces. We introduce WithEveryone, a unified framework for generating group images up to ten reference identities. WithEveryone injects each selected identity as an addressed token, predicts a structured identity--layout plan, and renders the plan as a visual condition. Its key objective, Layout-Grounded ID Loss, uses annotated face regions to supervise the intended identities directly, avoiding unstable embedding-based face matching; ID Representation Forcing additionally trains a prediction for each identity before image synthesis. On an identity-disjoint benchmark, WithEveryone achieves the highest target-context identity similarity, improving face similarity from 0.462 for GPT-Image-2 to 0.499, while reducing copy-paste artifacts from 0.169 to 0.055. It further covers 97.3\\% of the requested identities with a duplicate rate of only 2.8\\%. These results show that explicit identity--layout grounding enables identity-preserving generation to scale to larger groups without relying on direct reference-face copying.","upvotes":30,"discussionId":"6a87af9a89e517cbfd75dbc1","projectPage":"https://doby-xu.github.io/WithEveryone/","githubRepo":"https://github.com/doby-xu/WithEveryone","githubRepoAddedBy":"user","ai_summary":"WithEveryone enables reliable identity-preserving group image generation for up to ten people by grounding identities to layout plans and using region-based identity losses.","ai_keywords":["identity-preserving image generation","addressed token","identity--layout plan","Layout-Grounded ID Loss","ID Representation Forcing","identity-disjoint benchmark","target-context identity similarity"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":4,"organization":{"_id":"6645f953c39288df638dbdd5","name":"Tencent-Hunyuan","fullname":"Tencent Hunyuan","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d22496c58f969c152bcefd/woKSjt2wXvBNKussyYPsa.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"634bde123d11eaedd889e277","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1665916392312-noauth.png","isPro":false,"fullname":"Hengyuan Xu","user":"DobyXu","type":"user"},{"_id":"68f1c5e84806540fd1aa3eb9","avatarUrl":"/avatars/1726d59a7801ab88296b55eb78a1b009.svg","isPro":false,"fullname":"Ji Yumeng","user":"guojiangqianchilang","type":"user"},{"_id":"64cb54bcbb5d195b99186e15","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64cb54bcbb5d195b99186e15/Z7ziJXjGLXN5rBEYC0sqx.png","isPro":false,"fullname":"SII-Xingjun Ma","user":"xingjunm","type":"user"},{"_id":"655101623fe6c0b1f8b58987","avatarUrl":"/avatars/4d36a4988e6011fec3ceac2b59938c3a.svg","isPro":false,"fullname":"Jiabin Hua","user":"Ammmob","type":"user"},{"_id":"68ea07d4c9dda63b9d59eca3","avatarUrl":"/avatars/e37b415735bc33afe9a31a9248591db4.svg","isPro":false,"fullname":"WithAnyone","user":"WithAnyone","type":"user"},{"_id":"67ff545a3e4487750889023d","avatarUrl":"/avatars/38538ba7576e34741cd9d20c1834c1ab.svg","isPro":false,"fullname":"Tingshu Mou","user":"Multitray","type":"user"},{"_id":"64b914c8ace99c0723ad83a9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b914c8ace99c0723ad83a9/B4gxNByeVY_xaOcjwiN1j.jpeg","isPro":false,"fullname":"Wei Cheng","user":"wchengad","type":"user"},{"_id":"6685f80d6390df2eff39123f","avatarUrl":"/avatars/3d7c347c94979a7784267dd7a0c03a1d.svg","isPro":false,"fullname":"yiliucs","user":"yiliucs","type":"user"},{"_id":"6a476dbbd94f9dfc3733b8f0","avatarUrl":"/avatars/889f00d52238e19269b8d20ce96b8643.svg","isPro":false,"fullname":"tyc","user":"tyc111","type":"user"},{"_id":"63db6d6e06311e8b53e0072a","avatarUrl":"/avatars/9c9c9ca204fa4e4d6ad5d46899d26b09.svg","isPro":false,"fullname":"yangyiying","user":"yangyangyiying","type":"user"},{"_id":"6729d80b26cec81fa25edaa4","avatarUrl":"/avatars/1d6db3a3386f725443439fc86c58e4af.svg","isPro":false,"fullname":"Karamata","user":"SCFW2019","type":"user"},{"_id":"67d42f56fe3b3bee48d8f7b2","avatarUrl":"/avatars/290b0be37298baa47e94357e22f3e67e.svg","isPro":false,"fullname":"Lin","user":"hf857","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6645f953c39288df638dbdd5","name":"Tencent-Hunyuan","fullname":"Tencent Hunyuan","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d22496c58f969c152bcefd/woKSjt2wXvBNKussyYPsa.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.20336.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.20336 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.20336 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.20336 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.