{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T21:16:40Z","timestamp":1765228600684,"version":"3.46.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012477","name":"Key Project of Science and Technology Research Program of Chongqing Education Commission of China","doi-asserted-by":"publisher","award":["KJZD-K202300205"],"award-info":[{"award-number":["KJZD-K202300205"]}],"id":[{"id":"10.13039\/501100012477","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3585688","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T13:52:43Z","timestamp":1751637163000},"page":"11849-11862","source":"Crossref","is-referenced-by-count":0,"title":["CTIGEN-CDM: Controlled Text-to-Image Generation Using Cropped Diffusion Models"],"prefix":"10.1109","volume":"35","author":[{"given":"Yangpeng","family":"Liu","sequence":"first","affiliation":[{"name":"Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7995-092X","authenticated-orcid":false,"given":"Junjian","family":"Huang","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5048-0319","authenticated-orcid":false,"given":"Shiping","family":"Wen","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, Australian AI Institute, University of Technology at Sydney, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8652-8479","authenticated-orcid":false,"given":"Xing","family":"He","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5838-6247","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Feng","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref3","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref4","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref5","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ding"},{"key":"ref6","article-title":"You only sample once: Taming one-step text-to-image synthesis by self-cooperative diffusion GANs","author":"Luo","year":"2024","journal-title":"arXiv:2403.12931"},{"key":"ref7","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref8","article-title":"Improved vector quantized diffusion models","author":"Tang","year":"2022","journal-title":"arXiv:2205.16007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25133"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00817"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02065"},{"key":"ref17","article-title":"ELLA: Equip diffusion models with LLM for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"arXiv:2403.05135"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3485236"},{"key":"ref20","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3053408"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref24","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"van den Oord"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953753"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3347971"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274228"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3338459"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3131738"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00738"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00710"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00746"},{"key":"ref36","article-title":"ICE-bench: A unified and comprehensive benchmark for image creating and editing","author":"Pan","year":"2025","journal-title":"arXiv:2503.14482"},{"key":"ref37","article-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023","journal-title":"arXiv:2302.09778"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00591"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref45","first-page":"11127","article-title":"Uni-ControlNet: All-in-one control to text-to-image diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531390"},{"key":"ref48","article-title":"Locate, assign, refine: Taming customized promptable image inpainting","author":"Pan","year":"2024","journal-title":"arXiv:2403.19534"},{"key":"ref49","article-title":"OmniGen: Unified image generation","author":"Xiao","year":"2024","journal-title":"arXiv:2409.11340"},{"key":"ref50","article-title":"OminiControl: Minimal and universal control for diffusion transformer","author":"Tan","year":"2024","journal-title":"arXiv:2411.15098"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248659"},{"key":"ref52","first-page":"20662","article-title":"SnapFusion: Text-to-image diffusion model on mobile devices within two seconds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li"},{"key":"ref53","article-title":"Wuerstchen: An efficient architecture for large-scale text-to-image diffusion models","author":"Pernias","year":"2023","journal-title":"arXiv:2306.00637"},{"key":"ref54","first-page":"16716","article-title":"Structural pruning for diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Fang","year":"2023"},{"key":"ref55","article-title":"BK-SDM: A lightweight, fast, and cheap version of stable diffusion","author":"Kim","year":"2023","journal-title":"arXiv:2305.15798"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv.1412.6980","author":"Diederik","year":"2014"},{"key":"ref59","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu","year":"2022","journal-title":"arXiv:2202.09778"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref61","article-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","author":"Ranftl","year":"2019","journal-title":"arXiv:1907.01341"},{"key":"ref62","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"},{"key":"ref63","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NIPS","author":"Heusel"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11071319.pdf?arnumber=11071319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:42:47Z","timestamp":1765219367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11071319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":64,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3585688","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}