{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:09:04Z","timestamp":1784268544761,"version":"3.55.0"},"reference-count":53,"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":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171139"],"award-info":[{"award-number":["62171139"]}],"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\/iccv51701.2025.01703","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18325-18334","source":"Crossref","is-referenced-by-count":4,"title":["Unicombine: Unified Multi-Conditional Combination with Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Haoxuan","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinlong","family":"Peng","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingdong","family":"He","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Jin","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafu","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobin","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanjie","family":"Pan","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenye","family":"Gan","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingmin","family":"Chi","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai Ocean University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The OpenCV Library","author":"Bradski","year":"2000","journal-title":"Dr. Dobb\u2019s Journal of Software Tools"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref4","article-title":"Catvton: Concatenation is all you need for virtual try-on with diffusion models","author":"Chong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref6","author":"Esser","year":"2024","journal-title":"Scaling rectified flow transformers for high-resolution image synthesis"},{"key":"ref7","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00206"},{"key":"ref10","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Cocktail: Mixing multi-modality control for text-conditional im-age generation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Hu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref15","article-title":"Instantfamily: Masked attention for zero-shot multi-id image generation","author":"Kim","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref17","volume-title":"Flux","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4095"},{"key":"ref21","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref26","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref31","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","author":"Rout","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref33","article-title":"Styledrop: Text-to-image generation in any style","author":"Sohn","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Objectstitch: Generative object compositing","author":"Song","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref37","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","author":"Tan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888334"},{"key":"ref39","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref43","article-title":"Objectmate: A recurrence prior for object insertion and subject-driven generation","author":"Winter","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Csgo: Content-style composition in text-to-image generation","author":"Xing","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","volume-title":"Flux-controlnet-canny-diffusers","year":"2024"},{"key":"ref46","volume-title":"Flux-controlnet-depth-diffusers","year":"2024"},{"key":"ref47","volume-title":"Flux-ip-adapter","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref50","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"}],"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\/11445269.pdf?arnumber=11445269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:18Z","timestamp":1777530018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445269\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01703","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}