\n\t\n\t\t\n\t\n\t\n\t\tLinks 🔗:\n\t\n

👉 Subscribe: https://www.youtube.com/@Arxflix
👉 Twitter: https://x.com/arxflix
👉 LMNT (Partner): https://lmnt.com/

\n","updatedAt":"2024-06-08T22:24:55.471Z","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":176,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5070121884346008},"editors":["blanchon"],"editorAvatarUrls":["/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2312.02663","authors":[{"_id":"656fd910ec366e93ca2e26b1","name":"Yuxuan Yan","hidden":false},{"_id":"656fd910ec366e93ca2e26b2","user":{"_id":"64196320ed725fef64419c2a","avatarUrl":"/avatars/96feb22fb5e8931d6c9e0ea06148266f.svg","isPro":false,"fullname":"Chi Zhang","user":"DrChiZhang","type":"user"},"name":"Chi Zhang","status":"claimed_verified","statusLastChangedAt":"2023-12-06T12:00:36.414Z","hidden":false},{"_id":"656fd910ec366e93ca2e26b3","user":{"_id":"630443483926de1f7ec6bda0","avatarUrl":"/avatars/e8e95ab0d03f58c61846ccc1318502fe.svg","isPro":false,"fullname":"Rui Wang","user":"budui","type":"user"},"name":"Rui Wang","status":"claimed_verified","statusLastChangedAt":"2023-12-12T08:09:20.353Z","hidden":false},{"_id":"656fd910ec366e93ca2e26b4","name":"Pei Cheng","hidden":false},{"_id":"656fd910ec366e93ca2e26b5","user":{"_id":"63417332c5565a4b8d43a0d8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63417332c5565a4b8d43a0d8/MmnYG7Wu2Z_lqCBvTfJmy.png","isPro":false,"fullname":"Gang Yu","user":"skicy","type":"user"},"name":"Gang Yu","status":"admin_assigned","statusLastChangedAt":"2023-12-06T11:45:19.399Z","hidden":false},{"_id":"656fd910ec366e93ca2e26b6","name":"Bin Fu","hidden":false}],"publishedAt":"2023-12-05T11:02:45.000Z","submittedOnDailyAt":"2023-12-05T23:44:42.172Z","title":"FaceStudio: Put Your Face Everywhere in Seconds","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"This study investigates identity-preserving image synthesis, an intriguing\ntask in image generation that seeks to maintain a subject's identity while\nadding a personalized, stylistic touch. Traditional methods, such as Textual\nInversion and DreamBooth, have made strides in custom image creation, but they\ncome with significant drawbacks. These include the need for extensive resources\nand time for fine-tuning, as well as the requirement for multiple reference\nimages. To overcome these challenges, our research introduces a novel approach\nto identity-preserving synthesis, with a particular focus on human images. Our\nmodel leverages a direct feed-forward mechanism, circumventing the need for\nintensive fine-tuning, thereby facilitating quick and efficient image\ngeneration. Central to our innovation is a hybrid guidance framework, which\ncombines stylized images, facial images, and textual prompts to guide the image\ngeneration process. This unique combination enables our model to produce a\nvariety of applications, such as artistic portraits and identity-blended\nimages. Our experimental results, including both qualitative and quantitative\nevaluations, demonstrate the superiority of our method over existing baseline\nmodels and previous works, particularly in its remarkable efficiency and\nability to preserve the subject's identity with high fidelity.","upvotes":32,"discussionId":"656fd912ec366e93ca2e271f","githubRepo":"https://github.com/xyynafc/FaceStudio","githubRepoAddedBy":"auto","ai_summary":"A hybrid guidance framework for identity-preserving image synthesis efficiently generates stylistic portraits by combining stylized images, facial images, and textual prompts.","ai_keywords":["identity-preserving synthesis","Textual Inversion","DreamBooth","direct feed-forward mechanism","hybrid guidance framework","artistic portraits","identity-blended images","qualitative evaluations","quantitative evaluations"],"githubStars":311},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"61344ab1d19e49a35751462e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1630816930903-noauth.jpeg","isPro":false,"fullname":"Puffy Bird","user":"puffy310","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"62d25a6299febd9a27036a7d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d25a6299febd9a27036a7d/VO3tUtACXLCMXk3vM14th.jpeg","isPro":false,"fullname":"Taher ali badnawarwala","user":"tahercoolguy","type":"user"},{"_id":"64913551e319ebe474e9ee4d","avatarUrl":"/avatars/87ae52f54baa80d576306ddb6bcab63d.svg","isPro":false,"fullname":"rowan gim","user":"rowan-gim","type":"user"},{"_id":"647fa27d095af0bf116cd1b3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/647fa27d095af0bf116cd1b3/NIB5O1OgBQkIxwOag5FKj.jpeg","isPro":false,"fullname":"Meher Shashwat Nigam","user":"MeherShashwat","type":"user"},{"_id":"63054f9320668afe24865bba","avatarUrl":"/avatars/75962ffed33d38761bce6c947750e1e4.svg","isPro":false,"fullname":"KW","user":"kevineen","type":"user"},{"_id":"633a520aecbd8b19357b4806","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1664766468790-noauth.jpeg","isPro":false,"fullname":"Harsha Subramanyam","user":"ShadoWxShinigamI","type":"user"},{"_id":"63d8c72e255ef6add20a4b88","avatarUrl":"/avatars/ff28719b3ef5b82943dce15369e86bd5.svg","isPro":false,"fullname":"Hà Anh Tuấn","user":"tuanha1305","type":"user"},{"_id":"6362ddb7d3be91534c30bfd6","avatarUrl":"/avatars/dac76ebd3b8a08099497ec0b0524bc7c.svg","isPro":false,"fullname":"Art Atk","user":"ArtAtk","type":"user"},{"_id":"648eb1eb59c4e5c87dc116e0","avatarUrl":"/avatars/c636cea39c2c0937f01398c94ead5dad.svg","isPro":false,"fullname":"fdsqefsgergd","user":"T-representer","type":"user"},{"_id":"6343f83791049e1bce85373e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1665398834110-noauth.png","isPro":false,"fullname":"Zhang ning","user":"pe65374","type":"user"},{"_id":"64196320ed725fef64419c2a","avatarUrl":"/avatars/96feb22fb5e8931d6c9e0ea06148266f.svg","isPro":false,"fullname":"Chi Zhang","user":"DrChiZhang","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2312.02663

FaceStudio: Put Your Face Everywhere in Seconds

Published on Dec 5, 2023

· Submitted by

AK on Dec 5, 2023

Upvote

Authors:

Chi Zhang ,

Rui Wang ,

Gang Yu ,

Abstract

A hybrid guidance framework for identity-preserving image synthesis efficiently generates stylistic portraits by combining stylized images, facial images, and textual prompts.

AI-generated summary

This study investigates identity-preserving image synthesis, an intriguing task in image generation that seeks to maintain a subject's identity while adding a personalized, stylistic touch. Traditional methods, such as Textual Inversion and DreamBooth, have made strides in custom image creation, but they come with significant drawbacks. These include the need for extensive resources and time for fine-tuning, as well as the requirement for multiple reference images. To overcome these challenges, our research introduces a novel approach to identity-preserving synthesis, with a particular focus on human images. Our model leverages a direct feed-forward mechanism, circumventing the need for intensive fine-tuning, thereby facilitating quick and efficient image generation. Central to our innovation is a hybrid guidance framework, which combines stylized images, facial images, and textual prompts to guide the image generation process. This unique combination enables our model to produce a variety of applications, such as artistic portraits and identity-blended images. Our experimental results, including both qualitative and quantitative evaluations, demonstrate the superiority of our method over existing baseline models and previous works, particularly in its remarkable efficiency and ability to preserve the subject's identity with high fidelity.