{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:25:51Z","timestamp":1783787151720,"version":"3.55.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62472065"],"award-info":[{"award-number":["62472065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441231"],"award-info":[{"award-number":["62441231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2010"],"award-info":[{"award-number":["U23B2010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3613113","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:45:19Z","timestamp":1758563119000},"page":"9342-9353","source":"Crossref","is-referenced-by-count":7,"title":["StableIdentity: Inserting Anybody Into Anywhere at First Sight"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6908-5485","authenticated-orcid":false,"given":"Qinghe","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3168-3505","authenticated-orcid":false,"given":"Xu","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7202-6865","authenticated-orcid":false,"given":"Xiaomin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5409-6753","authenticated-orcid":false,"given":"Taiqing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0814-9876","authenticated-orcid":false,"given":"Liqian","family":"Ma","sequence":"additional","affiliation":[{"name":"ZMO.AI Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-4516","authenticated-orcid":false,"given":"Yunzhi","family":"Zhuge","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref3","article-title":"Text-to-image diffusion model in generative ai: A survey","author":"Zhang","year":"2023"},{"key":"ref4","article-title":"Pixart-$\\delta$: Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024"},{"key":"ref5","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref6","first-page":"72958","article-title":"Inserting anybody in diffusion models via celeb basis","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Yuan","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref8","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref9","first-page":"36777","article-title":"Pulid: Pure and lightning id customization via contrastive alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3322326"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3274990"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3314977"},{"key":"ref13","article-title":"Facechain: A playground for identity-preserving portrait generation","author":"Liu","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3281087"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405718"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s43503-023-00018-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"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":"10.1007\/s11263-025-02526-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531917"},{"key":"ref23","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref24","article-title":"Facestudio: Put your face everywhere in seconds","author":"Yan","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.081"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27891"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3297769"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3377540"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3278992"},{"key":"ref30","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530747"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref34","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018"},{"key":"ref35","article-title":"Logan: Latent optimisation for generative adversarial networks","author":"Wu","year":"2019"},{"key":"ref36","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"2020","author":"Ho","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref37","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref38","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"2021","author":"Dhariwal","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382484"},{"key":"ref40","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref41","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"2022","author":"Saharia","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00213"},{"key":"ref46","article-title":"Singleinsert: Inserting new concepts from a single image into text-to-image models for flexible editing","author":"Wu","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref50","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00623"},{"key":"ref52","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref54","article-title":"SDXL-lightning: Progressive adversarial diffusion distillation","author":"Lin","year":"2024"},{"key":"ref55","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01119"},{"key":"ref58","first-page":"578","article-title":"Bring metric functions into diffusion models","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"An","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref61","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":"ref62","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref63","article-title":"A learned representation for artistic style","author":"Dumoulin","year":"2016"},{"key":"ref64","first-page":"57500","article-title":"Customizable image synthesis with multiple subjects","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref68","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref69","first-page":"698","article-title":"Are GANs created equal? A large-scale study","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Lucic","year":"2018"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"issue":"1","key":"ref72","first-page":"3221","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","author":"Maaten","year":"2014","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11175426.pdf?arnumber=11175426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:34:52Z","timestamp":1766082892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11175426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3613113","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}