{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:08:46Z","timestamp":1784268526920,"version":"3.55.0"},"reference-count":88,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01814","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19513-19524","source":"Crossref","is-referenced-by-count":10,"title":["EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Yuxuan","family":"Zhang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yirui","family":"Yuan","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiren","family":"Song","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haofan","family":"Wang","sequence":"additional","affiliation":[{"name":"Liblib AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba group"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01166"},{"key":"ref7","article-title":"Wmadapter: Adding watermark control to latent diffusion models","author":"Ci","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","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":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref11","article-title":"Relationadapter: Learning and transferring visual relation with diffusion transformers","author":"Gong","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01774"},{"key":"ref13","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"Ace: Allround creator and editor following instructions via diffusion transformer","author":"Han","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Uniportrait: A unified framework for identity-preserving singleand multi-human image personalization","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00714"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32386"},{"key":"ref22","article-title":"Photodoodle: Learning artistic image editing from few-shot pairwise data","author":"Huang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref24","volume-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref26","volume-title":"Flux","year":"2024"},{"key":"ref27","volume-title":"FLUX.1-Redux-dev"},{"key":"ref28","article-title":"One diffusion to generate them all","author":"Duong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref30","first-page":"129","article-title":"Controlnet++: Improving conditional controls with efficient consistency feedback","volume-title":"European Conference on Computer Vision","author":"Li","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref34","volume-title":"yarn-art-Flux-LoRA"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref36","article-title":"Image watermarks are removable using controllable regeneration from clean noise","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i9.37697"},{"key":"ref38","first-page":"1","article-title":"Subjectdiffusion: Open domain personalized text-to-image generation without test-time fine-tuning","volume-title":"ACM SIGGRAPH 2024 Conference Papers","author":"Ma","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref42","article-title":"Itvton: Virtual try-on diffusion transformer model based on integrated image and text","author":"Ni","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref45","article-title":"Single-subject Personalization","journal-title":"Ms-diffusion: Multi-subject zero-shot image personalization with layout guidance"},{"key":"ref46","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Magic123: One image to high-quality 3 d object generation using both 2d and 3d diffusion priors","author":"Qian","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref49","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref53","volume-title":"FLUX.1-dev-LoRA-Text-Poster"},{"key":"ref54","volume-title":"FLUX.1-dev-LoRA-Vector-Journey"},{"key":"ref55","volume-title":"FLUX.1-dev-LoRA-Children-SimpleSketch"},{"key":"ref56","article-title":"Fonts: Text rendering with typography and style controls","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref57","article-title":"Wordcon: Word-level typography control in scene text rendering","author":"Shi","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref59","article-title":"Seededit: Align image re-generation to image editing","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref61","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref62","article-title":"Processpainter: Learn painting process from sequence data","author":"Song","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref63","article-title":"Anti-reference: Universal and immediate defense against reference-based generation","author":"Song","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00287"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01835"},{"key":"ref66","article-title":"Makeanything: Harnessing diffusion transformers for multidomain procedural sequence generation","author":"Song","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref67","article-title":"Omniconsistency: Learning style-agnostic consistency from paired stylization data","author":"Song","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref68","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","author":"Tan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref69","article-title":"Grid: Visual layout generation","author":"Wan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","article-title":"Stablegarment: Garment-centric generation via stable diffusion","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref72","article-title":"Diffdecompose: Layer-wise decomposition of alpha-composited images via diffusion transformers","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02657"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01241"},{"key":"ref76","article-title":"Anyrefill: A unified, data-efficient framework for left-prompt-guided vision tasks","author":"Xie","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1804"},{"key":"ref78","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref79","article-title":"Ipadapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_20"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3743093.3771013"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447042"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730702"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33123"},{"key":"ref88","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\/11444863.pdf?arnumber=11444863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:39Z","timestamp":1777613439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01814","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}