{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:44:44Z","timestamp":1778082284204,"version":"3.51.4"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62372482"],"award-info":[{"award-number":["62372482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation Youth Basic Research Program","award":["623B2100"],"award-info":[{"award-number":["623B2100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476293"],"award-info":[{"award-number":["62476293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2024YFE0203100"],"award-info":[{"award-number":["2024YFE0203100"]}]},{"name":"UAEU Start-Up Research","award":["G00005318"],"award-info":[{"award-number":["G00005318"]}]},{"name":"UAEU-ZU Joint Research Program","award":["G00005305"],"award-info":[{"award-number":["G00005305"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3652557","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:30Z","timestamp":1768255230000},"page":"5639-5654","source":"Crossref","is-referenced-by-count":7,"title":["ConsistentID: Portrait Generation With Multimodal Fine-Grained Identity Preserving"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3099-2886","authenticated-orcid":false,"given":"Jiehui","family":"Huang","sequence":"first","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9519-612X","authenticated-orcid":false,"given":"Xiao","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Zhuhai Campus, Sun Yat-Sen University, Zhuhai, China"}]},{"given":"Wenhui","family":"Song","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, China"}]},{"given":"Zheng","family":"Chong","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4258-1301","authenticated-orcid":false,"given":"Zhenchao","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4722-2183","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, China"}]},{"given":"Yuhao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Lenovo Research Group, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8083-0340","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Lenovo Research Group, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9838-6532","authenticated-orcid":false,"given":"Hanhui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, China"}]},{"given":"Yiqiang","family":"Yan","sequence":"additional","affiliation":[{"name":"Lenovo Research Group, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8941-2295","authenticated-orcid":false,"given":"Shengcai","family":"Liao","sequence":"additional","affiliation":[{"name":"CVLab College of Information Technology, United Arab Emirates University, Al Ain, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-Sen University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref2","article-title":"HyperHuman: Hyper-realistic human generation with latent structural diffusion","author":"Liu","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref6","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref8","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref9","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref12","article-title":"eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref13","first-page":"41693","article-title":"RAPHAEL: Text-to-image generation via large mixture of diffusion paths","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xue","year":"2023"},{"key":"ref14","article-title":"Fusion is all you need: Face fusion for customized identity-preserving image synthesis","author":"Mohamed","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref16","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"ref19","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref23","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555436"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","article-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023"},{"key":"ref33","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"issue":"2","key":"ref36","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"1","author":"Hu","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"ref38","article-title":"FaceStudio: Put your face everywhere in seconds","author":"Yan","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00829"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2019.00-42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICB2018.2018.00025"},{"key":"ref42","article-title":"SDEdit: Image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref44","first-page":"35202","article-title":"PHOTOSWAP: Personalized subject swapping in images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Gu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00206"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00345"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109036"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01406"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2023.08.003"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111451"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref55","first-page":"79320","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Qiu","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref57","article-title":"Synthetic faces high quality (SFHQ) dataset","author":"Beniaguev","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref60","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann","year":"2022"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref64","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_14"},{"key":"ref66","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref67","article-title":"FaceChain: A playground for identity-preserving portrait generation","author":"Liu","year":"2023"},{"key":"ref68","article-title":"EasyPhoto: Your smart AI photo generator","author":"Wu","year":"2023"},{"key":"ref69","first-page":"36777","article-title":"PuLID: Pure and lightning id customization via contrastive alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Guo","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01211"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11344798.pdf?arnumber=11344798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:15Z","timestamp":1775505375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11344798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":70,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3652557","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}