https://github.com/InstantID/InstantID

\n

Project Page: https://instantid.github.io/

\n","updatedAt":"2024-01-17T07:09:40.924Z","author":{"_id":"637745113a63a2983ffbde13","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1669187672174-637745113a63a2983ffbde13.jpeg","fullname":"Haofan Wang","name":"wanghaofan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":90}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6494141817092896},"editors":["wanghaofan"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1669187672174-637745113a63a2983ffbde13.jpeg"],"reactions":[],"isReport":false}},{"id":"65a8909b4623e107b96d99f4","author":{"_id":"645ca870680734460f9a9c79","avatarUrl":"/avatars/cbee433affd41d6fe09e30655c018ae5.svg","fullname":"Ototao","name":"ototao","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1},"createdAt":"2024-01-18T02:44:43.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2024-01-18T03:43:00.434Z","author":{"_id":"645ca870680734460f9a9c79","avatarUrl":"/avatars/cbee433affd41d6fe09e30655c018ae5.svg","fullname":"Ototao","name":"ototao","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}},{"id":"65a891625e79abfa2e20c0e8","author":{"_id":"643665d33193f279361cc292","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/643665d33193f279361cc292/k85RbhgQHp_gr2lLLOcgK.png","fullname":"wangqixun","name":"wangqixun","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":40},"createdAt":"2024-01-18T02:48:02.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2024-01-22T14:03:44.947Z","author":{"_id":"643665d33193f279361cc292","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/643665d33193f279361cc292/k85RbhgQHp_gr2lLLOcgK.png","fullname":"wangqixun","name":"wangqixun","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":40}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}},{"id":"65a891b8a92d5908df1bbf70","author":{"_id":"645ca870680734460f9a9c79","avatarUrl":"/avatars/cbee433affd41d6fe09e30655c018ae5.svg","fullname":"Ototao","name":"ototao","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1},"createdAt":"2024-01-18T02:49:28.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2024-01-18T03:43:13.306Z","author":{"_id":"645ca870680734460f9a9c79","avatarUrl":"/avatars/cbee433affd41d6fe09e30655c018ae5.svg","fullname":"Ototao","name":"ototao","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}},{"id":"65ae747769cd2991ef08eb4f","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264},"createdAt":"2024-01-22T13:58:15.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation](https://huggingface.co/papers/2312.16272) (2023)\n* [When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation](https://huggingface.co/papers/2311.17461) (2023)\n* [FaceStudio: Put Your Face Everywhere in Seconds](https://huggingface.co/papers/2312.02663) (2023)\n* [PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization](https://huggingface.co/papers/2312.06354) (2023)\n* [DreamTuner: Single Image is Enough for Subject-Driven Generation](https://huggingface.co/papers/2312.13691) (2023)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

\n

The following papers were recommended by the Semantic Scholar API

\n

\n
• SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation (2023)
\n
• When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation (2023)
\n
• FaceStudio: Put Your Face Everywhere in Seconds (2023)
\n
• PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization (2023)
\n
• DreamTuner: Single Image is Enough for Subject-Driven Generation (2023)
\n

\n

Please give a thumbs up to this comment if you found it helpful!

\n

If you want recommendations for any Paper on Hugging Face checkout this Space

\n","updatedAt":"2024-01-22T13:58:15.254Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6938886046409607},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[{"reaction":"👍","users":["ma-topia"],"count":1}],"isReport":false}},{"id":"65e5ca49a9b6993b336d40c8","author":{"_id":"65e202cbfd93c9945a73dfcd","avatarUrl":"/avatars/9eb18c8681449766e451a150a4e1bda9.svg","fullname":"sdxfghj","name":"10x41","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false},"createdAt":"2024-03-04T13:19:05.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"\n\n","html":"

\n","updatedAt":"2024-03-04T13:19:05.153Z","author":{"_id":"65e202cbfd93c9945a73dfcd","avatarUrl":"/avatars/9eb18c8681449766e451a150a4e1bda9.svg","fullname":"sdxfghj","name":"10x41","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false}},"numEdits":0,"identifiedLanguage":{"language":"fr","probability":0.32270628213882446},"editors":["10x41"],"editorAvatarUrls":["/avatars/9eb18c8681449766e451a150a4e1bda9.svg"],"reactions":[],"isReport":false}},{"id":"6664c59912668a9185fbce1e","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":142},"createdAt":"2024-06-08T20:56:57.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"# InstantID: Revolutionary Zero-Shot Image Personalization!\n\nhttps://cdn-uploads.huggingface.co/production/uploads/6186ddf6a7717cb375090c01/swj3lG6tdUKDAQujAcyrx.mp4 \n\n## Links 🔗:\n👉 Subscribe: https://www.youtube.com/@Arxflix\n👉 Twitter: https://x.com/arxflix\n👉 LMNT (Partner): https://lmnt.com/\n\n\nBy Arxflix\n","html":"

InstantID: Revolutionary Zero-Shot Image Personalization!

\n

\n\n

Links 🔗:

\n

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

\n

By Arxflix

\n","updatedAt":"2024-06-08T20:56:57.928Z","author":{"_id":"6186ddf6a7717cb375090c01","avatarUrl":"/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg","fullname":"Julien BLANCHON","name":"blanchon","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":142}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.4981689155101776},"editors":["blanchon"],"editorAvatarUrls":["/avatars/716b6a7d1094c8036b2a8a7b9063e8aa.svg"],"reactions":[],"isReport":false}},{"id":"674762d4dace2ad7d49a52be","author":{"_id":"6745ebf7cc76d3faa939108c","avatarUrl":"/avatars/8c1ded322299ccdbb7490db260dde4ac.svg","fullname":"Лиана Хасанова","name":"Lina0701","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false},"createdAt":"2024-11-27T18:20:04.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"\n\n\n","html":"

\n","updatedAt":"2024-11-27T18:20:04.700Z","author":{"_id":"6745ebf7cc76d3faa939108c","avatarUrl":"/avatars/8c1ded322299ccdbb7490db260dde4ac.svg","fullname":"Лиана Хасанова","name":"Lina0701","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.49344202876091003},"editors":["Lina0701"],"editorAvatarUrls":["/avatars/8c1ded322299ccdbb7490db260dde4ac.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2401.07519","authors":[{"_id":"65a76b903d3c83940823ebbe","user":{"_id":"643665d33193f279361cc292","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/643665d33193f279361cc292/k85RbhgQHp_gr2lLLOcgK.png","isPro":false,"fullname":"wangqixun","user":"wangqixun","type":"user"},"name":"Qixun Wang","status":"admin_assigned","statusLastChangedAt":"2024-01-17T09:14:57.341Z","hidden":false},{"_id":"65a76b903d3c83940823ebbf","name":"Xu Bai","hidden":false},{"_id":"65a76b903d3c83940823ebc0","user":{"_id":"637745113a63a2983ffbde13","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1669187672174-637745113a63a2983ffbde13.jpeg","isPro":false,"fullname":"Haofan Wang","user":"wanghaofan","type":"user"},"name":"Haofan Wang","status":"extracted_confirmed","statusLastChangedAt":"2024-04-25T02:59:36.296Z","hidden":false},{"_id":"65a76b903d3c83940823ebc1","name":"Zekui Qin","hidden":false},{"_id":"65a76b903d3c83940823ebc2","user":{"_id":"6311d9ee04f842f79916158c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/PvOYgDEpe0x5ExLyj1BK-.png","isPro":false,"fullname":"chen","user":"antonio-c","type":"user"},"name":"Anthony Chen","status":"claimed_verified","statusLastChangedAt":"2024-11-05T07:59:11.348Z","hidden":false}],"publishedAt":"2024-01-15T07:50:18.000Z","submittedOnDailyAt":"2024-01-17T03:24:30.078Z","title":"InstantID: Zero-shot Identity-Preserving Generation 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":"There has been significant progress in personalized image synthesis with\nmethods such as Textual Inversion, DreamBooth, and LoRA. Yet, their real-world\napplicability is hindered by high storage demands, lengthy fine-tuning\nprocesses, and the need for multiple reference images. Conversely, existing ID\nembedding-based methods, while requiring only a single forward inference, face\nchallenges: they either necessitate extensive fine-tuning across numerous model\nparameters, lack compatibility with community pre-trained models, or fail to\nmaintain high face fidelity. Addressing these limitations, we introduce\nInstantID, a powerful diffusion model-based solution. Our plug-and-play module\nadeptly handles image personalization in various styles using just a single\nfacial image, while ensuring high fidelity. To achieve this, we design a novel\nIdentityNet by imposing strong semantic and weak spatial conditions,\nintegrating facial and landmark images with textual prompts to steer the image\ngeneration. InstantID demonstrates exceptional performance and efficiency,\nproving highly beneficial in real-world applications where identity\npreservation is paramount. Moreover, our work seamlessly integrates with\npopular pre-trained text-to-image diffusion models like SD1.5 and SDXL, serving\nas an adaptable plugin. Our codes and pre-trained checkpoints will be available\nat https://github.com/InstantID/InstantID.","upvotes":57,"discussionId":"65a76b963d3c83940823ec78","projectPage":"https://instantid.github.io/","githubRepo":"https://github.com/instantX-research/InstantID","ai_summary":"InstantID is a diffusion model-based solution for personalized image synthesis that uses a single facial image and integrates with pre-trained models while maintaining high face fidelity and efficiency.","ai_keywords":["Textual Inversion","DreamBooth","LoRA","ID embedding-based methods","diffusion model","plug-and-play module","IdentityNet","semantic conditions","spatial conditions","facial images","landmark images","textual prompts","identity preservation","SD1.5","SDXL"],"githubStars":11825},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6303eae7a362e7e8b51cf113","avatarUrl":"/avatars/9224931167edca92ade4e49728fbc5d5.svg","isPro":false,"fullname":"Michael Hale","user":"mhale","type":"user"},{"_id":"6416489606af02514d0b9ef7","avatarUrl":"/avatars/00eb232d6b325514512c2f535aef381b.svg","isPro":false,"fullname":"Roberto Ramírez","user":"rr-16","type":"user"},{"_id":"61a0ef790fb4c1bd3c63429a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61a0ef790fb4c1bd3c63429a/tjceTkdPhBMGETYonhok5.jpeg","isPro":false,"fullname":"Chris","user":"chr7stos","type":"user"},{"_id":"6342ac8ef4f36a39f62ce413","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6342ac8ef4f36a39f62ce413/WUrNG71NsHkY0JJCCG-4D.jpeg","isPro":false,"fullname":"Emre Sokullu","user":"esokullu","type":"user"},{"_id":"63c5d43ae2804cb2407e4d43","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1673909278097-noauth.png","isPro":false,"fullname":"xziayro","user":"xziayro","type":"user"},{"_id":"64b89510126cfeb8fdcddb61","avatarUrl":"/avatars/13a65ec50313a7ae606560e10b6444e4.svg","isPro":false,"fullname":"wu","user":"shadow-none","type":"user"},{"_id":"63f1e3ccbe95ed4c9a94eb93","avatarUrl":"/avatars/7c233d7872a0da6d022df2524e1c6697.svg","isPro":false,"fullname":"haluk türken","user":"haluk","type":"user"},{"_id":"637745113a63a2983ffbde13","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1669187672174-637745113a63a2983ffbde13.jpeg","isPro":false,"fullname":"Haofan Wang","user":"wanghaofan","type":"user"},{"_id":"64747f7e33192631bacd8831","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64747f7e33192631bacd8831/dstkZJ4sHJSeqLesV5cOC.jpeg","isPro":false,"fullname":"Taufiq Dwi Purnomo","user":"taufiqdp","type":"user"},{"_id":"61868ce808aae0b5499a2a95","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61868ce808aae0b5499a2a95/F6BA0anbsoY_Z7M1JrwOe.jpeg","isPro":true,"fullname":"Sylvain Filoni","user":"fffiloni","type":"user"},{"_id":"638f06ee7559bf9a2b2b003f","avatarUrl":"/avatars/6efafaa4387afd9ad33ec9504e2e09de.svg","isPro":false,"fullname":"quincy","user":"quincy003","type":"user"},{"_id":"6553490e019ece3424105f6c","avatarUrl":"/avatars/7eecf207bd524df8f0bbe6a2c71659c8.svg","isPro":false,"fullname":"tx fu","user":"nono1216","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":1}">