{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:14Z","timestamp":1777890134215,"version":"3.51.4"},"reference-count":87,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192781,62172326,62137002"],"award-info":[{"award-number":["62192781,62172326,62137002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00982","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10549-10559","source":"Crossref","is-referenced-by-count":9,"title":["DynamicID: Zero-Shot Multi-ID Image Personalization With Flexible Facial Editability"],"prefix":"10.1109","author":[{"given":"Xirui","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University,MOEKLINNS Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University,MOEKLINNS Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Western Movie Group,Film AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weizhan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University,MOEKLINNS Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Western Movie Group,Film AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yikun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University,MOEKLINNS Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haishun","family":"Nan","sequence":"additional","affiliation":[{"name":"Western Movie Group,Film AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687604"},{"key":"ref2","volume-title":"Synthetic faces high quality (sfhq) dataset","author":"Beniaguev","year":"2022"},{"key":"ref3","article-title":"Gradient-free training of recurrent neural networks","author":"Bolager","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Instructbooth: Instruction-following personalized text-toimage generation","author":"Chae","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00824"},{"key":"ref6","article-title":"Disenbooth: Identitypreserving disentangled tuning for subject-driven text-toimage generation","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref7","article-title":"Photoverse: Tuning-free image customization with text-to-image diffusion models","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","article-title":"Subject-driven text-to-image generation via apprenticeship learning","author":"Chen","year":"2023","journal-title":"NeurIPS"},{"key":"ref9","article-title":"Id-aligner: Enhancing identitypreserving text-to-image generation with reward feedback learning","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27891"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref12","article-title":"Magicid: Flexible id fidelity generation system","author":"Deng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02526-z"},{"key":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ICML"},{"key":"ref15","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_19"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/02699930701626582"},{"key":"ref18","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","author":"Gu","year":"2023","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Pulid: Pure and lightning ID customization via contrastive alignment","author":"Guo","year":"2024","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_2"},{"key":"ref21","article-title":"Vico: Plug-and-play visual condition for personalized text-to-image generation","author":"Hao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Uniportrait: A unified framework for identity-preserving singleand multi-human image personalization","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref25","article-title":"Dreamtuner: Single image is enough for subject-driven generation","author":"Hua","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3652557"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref31","article-title":"Instantfamily: Masked attention for zero-shot multi-id image generation","author":"Kim","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref34","volume-title":"Flux","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref36","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-toimage generation and editing","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01183"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02201"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref40","article-title":"When stylegan meets stable diffusion: a w+ adapter for personalized image generation","author":"Li","year":"2024","journal-title":"CVPR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00612"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104026"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00206"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref46","article-title":"Cones 2: Customizable image synthesis with multiple subjects","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref48","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2022","journal-title":"ICML"},{"key":"ref49","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"ref51","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2024","journal-title":"ICLR"},{"key":"ref52","article-title":"Luminaimage 2.0: A unified and efficient image generative framework","author":"Qin","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","author":"Qiu","year":"2023","journal-title":"NeurIPS"},{"key":"ref54","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref55","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3521321"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref60","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref62","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref63","article-title":"LAION-5B: an open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00654"},{"key":"ref65","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref66","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","author":"Team","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref67","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"NeurIPS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"ref69","article-title":"Oneactor: Consistent subject generation via clusterconditioned guidance","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32831"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687662"},{"key":"ref72","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3613113"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01248"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00733"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_15"},{"key":"ref78","article-title":"Infinite-id: Identity-preserved personalization via idsemantics decoupling paradigm","author":"Wu","year":"2024","journal-title":"ECCV"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref81","article-title":"Facestudio: Put your face everywhere in seconds","author":"Yan","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref82","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref84","article-title":"Flashface: Human image personalization with high-fidelity identity preservation","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref85","article-title":"Panollama: Generating endless and coherent panoramas with next-token-prediction 11 ms","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref86","article-title":"Storymaker: Towards holistic consistent characters in text-to-image generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_8"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444210.pdf?arnumber=11444210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:31Z","timestamp":1777613371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00982","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}