{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:21Z","timestamp":1784268621315,"version":"3.55.0"},"reference-count":76,"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\/iccv51701.2025.01552","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16712-16722","source":"Crossref","is-referenced-by-count":4,"title":["DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models"],"prefix":"10.1109","author":[{"given":"Dewei","family":"Zhou","sequence":"first","affiliation":[{"name":"Zhejiang University,RELER, CCAI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingwei","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University,RELER, CCAI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongxin","family":"Yang","sequence":"additional","affiliation":[{"name":"Harvard University,DBMI, HMS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University,RELER, CCAI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Balaji","year":"2022","journal-title":"ediff-i: Text-to-image diffusion models with ensemble of expert denoisers"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657525"},{"key":"ref3","article-title":"Black forest labs; frontier ai lab, 2024","year":"2024","journal-title":"Black forest labs; frontier ai lab"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00630"},{"key":"ref5","author":"Chen","year":"2024","journal-title":"Region-aware text-to-image generation via hard binding and soft refinement"},{"key":"ref6","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","volume-title":"ICLR 2023 (Eleventh International Conference on Learning Representations)","author":"Couairon","year":"2023"},{"key":"ref7","author":"Dalva","year":"2024","journal-title":"Fluxspace: Disentangled semantic editing in rectified flow transformers"},{"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":"Hierarchical text-conditional image generation with clip latents, 2022","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref10","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"ICLR","author":"Feng","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref12","author":"Gao","year":"2024","journal-title":"Eraseanything: Enabling concept erasure in rectified flow transformers"},{"key":"ref13","first-page":"2207.12598","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00681"},{"key":"ref15","article-title":"Auto-encoding variational bayes, 2013","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","author":"Kong","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1868"},{"key":"ref19","article-title":"Regiondiffusion: Generative data augmentation for object detection with diffusion models","author":"Li","year":"2024","journal-title":"SSRN Electronic Journal"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754546"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754548"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01126"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2537"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref26","author":"Li","year":"2024","journal-title":"Anysynth: Harnessing the power of image synthetic data generation for generalized vision-language tasks"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00377"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00612"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01713"},{"key":"ref30","author":"Lin","year":"2024","journal-title":"Ctrl-adapter: An efficient and versatile framework for adapting diverse controls to any diffusion model"},{"key":"ref31","article-title":"Microsoft coco: Common objects in context, 2015","author":"Lin","year":"2015","journal-title":"Microsoft coco: Common objects in context"},{"key":"ref32","author":"Liu","year":"2024","journal-title":"Playground v3: Improving text-to-image alignment with deep-fusion large language models"},{"key":"ref33","author":"Liu","year":"2022","journal-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_1"},{"key":"ref35","author":"Liu","year":"2025","journal-title":"Cot-lized diffusion: Let\u2019s reinforce t2i generation step-by-step"},{"key":"ref36","article-title":"Parasolver: A hierarchical parallel integral solver for diffusion models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Lu","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00615"},{"key":"ref39","author":"Lu","year":"2024","journal-title":"Robust watermarking using generative priors against image editing: From benchmarking to advances"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref41","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"ICML","author":"Nichol","year":"2022"},{"key":"ref42","author":"Peng","year":"2024","journal-title":"Controlnext: Powerful and efficient control for image and video generation"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref44","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref45","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"issue":"140","key":"ref46","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref47","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref48","article-title":"High-resolution image synthesis with latent diffusion models, 2022","author":"Rombach","year":"2022","journal-title":"High-resolution image synthesis with latent diffusion models"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref50","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"NIPS","author":"Saharia","year":"2022"},{"key":"ref51","author":"Stan","year":"2023","journal-title":"Ldm3d: Latent diffusion model for 3d"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","article-title":"Instancediffusion: Instance-level control for image generation, 2024","author":"Wang","year":"2024","journal-title":"Instancediffusion: Instance-level control for image generation"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00739"},{"key":"ref55","author":"Wu","year":"2024","journal-title":"Ifadapter: Instance feature control for grounded text-to-image generation"},{"key":"ref56","author":"Xiao","year":"2023","journal-title":"R&b: Region and boundary aware zero-shot grounded text-to-image generation"},{"key":"ref57","first-page":"2404.01717","author":"Xie","year":"2024","journal-title":"Addsr: Accelerating diffusion-based blind super-resolution with adversarial diffusion distillation"},{"key":"ref58","author":"Xu","year":"2024","journal-title":"Ctrlora: An extensible and efficient framework for controllable image generation"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref60","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref61","author":"Ye","year":"2023","journal-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models"},{"key":"ref62","article-title":"Scaling autoregressive models for content-rich text-to-image generation, 2022","author":"Yu","year":"2022","journal-title":"Scaling autoregressive models for content-rich text-to-image generation"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01126"},{"key":"ref64","author":"Zhang","year":"2024","journal-title":"Creatilayout: Siamese multimodal diffusion transformer for creative layout-to-image generation"},{"key":"ref65","author":"Zhang","year":"2025","journal-title":"Creatidesign: A unified multi-conditional diffusion transformer for creative graphic design"},{"key":"ref66","author":"Zhang","year":"2025","journal-title":"Seg2any: Open-set segmentation-mask-to-image generation with precise shape and semantic control"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00791"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106428"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2026.3660483"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01671"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/199"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref74","article-title":"Migc++: Advanced multi-instance generation controller for image synthesis, 2024","author":"Zhou","year":"2024","journal-title":"Migc++: Advanced multi-instance generation controller for image synthesis"},{"key":"ref75","author":"Zhou","year":"2024","journal-title":"3dis: Depth-driven decoupled instance synthesis for text-to-image generation"},{"key":"ref76","author":"Zhou","year":"2025","journal-title":"3dis-flux: simple and efficient multi-instance generation with dit rendering"}],"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\/11445472.pdf?arnumber=11445472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:45:07Z","timestamp":1777578307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01552","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}