{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:03:10Z","timestamp":1770739390437,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425603"],"award-info":[{"award-number":["62425603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20240011"],"award-info":[{"award-number":["BK20240011"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3628109","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:44:48Z","timestamp":1762195488000},"page":"2296-2311","source":"Crossref","is-referenced-by-count":0,"title":["Refine, Control and Distill: A Text-to-Image Framework for Faithful Image Generation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2307-5393","authenticated-orcid":false,"given":"Peng","family":"Xing","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4937-6784","authenticated-orcid":false,"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6249-5596","authenticated-orcid":false,"given":"Yanpeng","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref4","article-title":"Divide & bind your attention for improved generative semantic nursing","volume-title":"Proc. BMVC","author":"Li","year":"2023"},{"key":"ref5","first-page":"3536","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Rassin","year":"2024"},{"key":"ref6","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NeurIPS","author":"Saharia","year":"2022"},{"key":"ref7","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref8","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref16","first-page":"1590","article-title":"A text-to-picture synthesis system for augmenting communication","volume-title":"Proc. AAAI","author":"Zhu","year":"2007"},{"key":"ref17","first-page":"30105","article-title":"StyleGAN-T: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sauer","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho","year":"2020"},{"key":"ref22","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref24","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref27","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref28","article-title":"eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530104"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref31","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"ref34","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hertz","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref36","article-title":"Diffusion self-guidance for controllable image generation","author":"Epstein","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00984"},{"key":"ref40","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"ref44","article-title":"Pretraining is all you need for image-to-image translation","author":"Wang","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02065"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref48","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Feng","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"ref50","first-page":"26291","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang","year":"2023"},{"key":"ref51","article-title":"Dreamrenderer: Taming multi-instance attribute control in large-scale text-to-image models","author":"Zhou","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref55","article-title":"spCy2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing","author":"Honnibal","year":"2017"},{"key":"ref56","article-title":"Dragondiffusion: Enabling drag-style manipulation on diffusion models","author":"Mou","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_20"},{"key":"ref61","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"issue":"3","key":"ref63","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Comput. Sci."},{"key":"ref64","first-page":"78723","article-title":"T2I-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","volume":"36","author":"Huang","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref65","article-title":"Pixart-$alpha$alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"ref67","article-title":"ELLA: Equip diffusion models with LLM for enhanced semantic alignment","author":"Hu","year":"2024"},{"key":"ref68","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11223996.pdf?arnumber=11223996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:56Z","timestamp":1770671156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":68,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3628109","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}