{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:45:01Z","timestamp":1778694301016,"version":"3.51.4"},"reference-count":73,"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\/iccv51701.2025.01480","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15949-15959","source":"Crossref","is-referenced-by-count":1,"title":["IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Yinwei","family":"Wu","sequence":"first","affiliation":[{"name":"Tencent PCG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianpan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Ma","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Su","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Ma","sequence":"additional","affiliation":[{"name":"Tencent PCG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref3","author":"Bai","year":"2023","journal-title":"Qwen technical report"},{"key":"ref4","article-title":"Imagen 3","author":"Baldridge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"1737","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"International Conference on Machine Learning","author":"Bar-Tal","year":"2023"},{"issue":"3","key":"ref6","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref7","volume-title":"bluexspencil-xl","year":"2024"},{"key":"ref8","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref10","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Layoutdiffuse: Adapting foundational dif-fusion models for layout-to-image generation","author":"Cheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref13","volume-title":"claymation-style-lora","year":"2024"},{"key":"ref14","author":"Feng","journal-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01480"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref17","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Neural Information Processing Systems, Neural Information Processing Systems"},{"key":"ref18","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Neural Information Processing Systems, Neural Information Processing Systems"},{"key":"ref20","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2913372"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3652557"},{"key":"ref23","article-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref27","article-title":"Dag: Depthaware guidance with denoising diffusion probabilistic models","author":"Kim","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01356"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref34","volume-title":"lelo-lego","year":"2024"},{"key":"ref35","first-page":"5","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref38","volume-title":"Pixel art xl","year":"2023"},{"key":"ref39","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"2","key":"ref41","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref46","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Photorealistic text-to-image diffusion models with deep language understanding"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01063"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078577"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16368"},{"key":"ref51","article-title":"Retrieving conditions from reference images for diffusion models","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00763"},{"key":"ref55","article-title":"Instantstyle-plus: Style transfer with content-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","author":"Wang","year":"2023","journal-title":"Cogvlm: Visual expert for pretrained language models"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28429"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00734"},{"key":"ref62","article-title":"R&b: Region and boundary aware zeroshot grounded text-to-image generation","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02160"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref66","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"When and why visionlanguage models behave like bags-of-words, and what to do about it?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yuksekgonul","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref72","article-title":"Migc++: Advanced multi-instance generation controller for image synthesis","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"}],"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\/11446292.pdf?arnumber=11446292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:13Z","timestamp":1777612873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01480","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}