{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T17:11:25Z","timestamp":1781197885226,"version":"3.54.1"},"reference-count":63,"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\/501100001459","name":"Ministry of Education, Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","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\/iccv51701.2025.01386","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14940-14950","source":"Crossref","is-referenced-by-count":10,"title":["OminiControl: Minimal and Universal Control for Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Zhenxiong","family":"Tan","sequence":"first","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songhua","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyi","family":"Yang","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiaochu","family":"Xue","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","author":"Bar-Tal","year":"2023","journal-title":"Multidiffusion: Fusing diffusion paths for controlled image generation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01718"},{"key":"ref4","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Pixart- $\\{\\backslash \\operatorname{delta}\\}$: Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Style-friendly snr sampler for style-driven generation","author":"Choi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","year":"2024","journal-title":"Peak signal-to-noise ratio"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICECA.2018.8474715"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref10","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref12","article-title":"Ace: All-round creator and editor following instructions via diffusion transformer","author":"Han","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","volume-title":"Text-to-image-2m dataset","author":"Hate","year":"2024"},{"key":"ref14","author":"He","year":"2025","journal-title":"Anystory: Towards unified single and multiple subject personalization in text-to-image generation"},{"key":"ref15","author":"He","year":"2024","journal-title":"Dynamiccontrol: Adaptive condition selection for improved text-to-image generation"},{"key":"ref16","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":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","author":"Hua","year":"2023","journal-title":"Dreamtuner: Single image is enough for subject-driven generation"},{"key":"ref19","author":"Huang","year":"2024","journal-title":"Group diffusion transformers are unsupervised multitask learners"},{"key":"ref20","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref22","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref24","year":"2024","journal-title":"Flux: Official inference repository for flux. 1 models"},{"key":"ref25","volume-title":"Flux.1-dev-controlnet-union-pro","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref29","author":"Li","year":"2025","journal-title":"Controlar: Controllable image generation with autoregressive models"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4095"},{"key":"ref31","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref33","author":"Ma","year":"2024","journal-title":"Character-adapter: Prompt-guided region control for highfidelity character customization"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00207"},{"key":"ref35","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Prodigy: An expeditiously adaptive parameter-free learner","volume-title":"Forty-first International Conference on Machine Learning","author":"Mishchenko","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref38","article-title":"Kosmos-g: Generating images in context with multimodal large language models","author":"Pan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Multimodal attention for speech emotion recognition","author":"Pan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref45","first-page":"234","article-title":"Unet: Convolutional networks for biomedical image segmentation","volume-title":"Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference","author":"Ronneberger","year":"2015"},{"key":"ref46","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref54","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref58","volume-title":"Flux-ip-adapter","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"ref60","article-title":"Ipadapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"}],"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\/11445439.pdf?arnumber=11445439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:09Z","timestamp":1777611729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01386","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}