{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:43Z","timestamp":1777865383693,"version":"3.51.4"},"reference-count":68,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB3203500"],"award-info":[{"award-number":["2022YFB3203500"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01440","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15521-15531","source":"Crossref","is-referenced-by-count":0,"title":["FreeCus: Free Lunch Subject-Driven Customization in Diffusion Transformers"],"prefix":"10.1109","author":[{"given":"Yanbing","family":"Zhang","sequence":"first","affiliation":[{"name":"ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Zhou","sequence":"additional","affiliation":[{"name":"ECUST,Key Laboratory of Smart Manufacturing in Energy Chemical Process,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengping","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Academy of Al for Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"ref2","article-title":"Building normalizing flows with stochastic interpolants","volume-title":"The Eleventh International Conference on Learning Representations","author":"Albergo"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687590"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00738"},{"key":"ref7","article-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"2024","volume-title":"Black Forest Labs. Announcing black forest labs","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"arXiv preprint","author":"Chen","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687612"},{"key":"ref15","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref16","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref17","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref19","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hertz"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"47","key":"ref24","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","article-title":"Lora: Lowrank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref26","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref28","article-title":"Openclip, 2021","author":"Ilharco","journal-title":"If you use this software, please cite it as below"},{"key":"ref29","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","article-title":"Anymaker: Zero-shot general object customization via decoupled dual-level id injection","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Flowedit: Inversion-free text-based editing using pre-trained flow models","author":"Kulikov","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref35","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref36","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Liu"},{"key":"ref37","author":"Lu","year":"2024","journal-title":"Qwen2vl-flux: Unifying image and text guidance for controllable image generation"},{"key":"ref38","article-title":"Realcustom++: Representing images as real-word for real-time customization","author":"Mao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref40","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Kosmos-g: Generating images in context with multimodal large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Pan"},{"key":"ref42","article-title":"$\\lambda$-eclipse: Multi-concept personalized text-to-image diffusion models by leveraging clip latent space","author":"Patel","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","article-title":"Dreambench++: A human-aligned benchmark for personalized image generation","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-658-47422-5_60","article-title":"W\u00fcrstchen: An efficient architecture for large-scale text-to-image diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Pernias"},{"key":"ref46","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref52","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref55","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","volume":"3","author":"Tan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref57","article-title":"Add-it: Training-free object insertion in images with pretrained diffusion models","author":"Tewel","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref59","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Ms-diffusion: Multi-subject zero-shot image per-sonalization with layout guidance","author":"Wang","year":"2024","journal-title":"CoRR, abs\/2406.07209"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref64","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.26599\/AIR.2024.9150038"},{"key":"ref68","article-title":"Lumina-next: Making lumina-t2x stronger and faster with next-dit","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zhuo"}],"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\/11444688.pdf?arnumber=11444688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:11Z","timestamp":1777530191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444688\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01440","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}