{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:57:12Z","timestamp":1784300232226,"version":"3.55.0"},"reference-count":336,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Young Scientists Fund of NSFC","award":["62406035"],"award-info":[{"award-number":["62406035"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2025.3646548","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T18:58:30Z","timestamp":1766170710000},"page":"4771-4791","source":"Crossref","is-referenced-by-count":18,"title":["Controllable Generation With Text-to-Image Diffusion Models: A Survey"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4717-1539","authenticated-orcid":false,"given":"Pu","family":"Cao","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4616-2200","authenticated-orcid":false,"given":"Qing","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3857-3982","authenticated-orcid":false,"given":"Lu","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref7","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref8","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann","year":"2022"},{"key":"ref9","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref10","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref11","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref12","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref13","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref16","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref17","article-title":"eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref18","article-title":"PhotoVerse: Tuning-free image customization with text-to-image diffusion models","author":"Chen","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref20","article-title":"Efficient diffusion models for vision: A survey","author":"Ulhaq","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305243"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref24","article-title":"Generative AI meets 3D: A survey on text-to-3D in AIGC era","author":"Li","year":"2023"},{"key":"ref25","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref26","article-title":"Flow matching for generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lipman","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref28","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref29","article-title":"Flux","author":"Labs","year":"2024"},{"key":"ref30","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"1","key":"ref32","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref34","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":"ref35","article-title":"DeepFloyd IF: A modular cascaded text-to-image model","year":"2023"},{"key":"ref36","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref37","article-title":"PixArt-$\\alpha$\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00823"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00745"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01711"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref44","first-page":"8542","article-title":"In-context learning unlocked for diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02435-1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613832"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02110"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28550"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00260"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_27"},{"key":"ref51","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref52","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans","year":"2016"},{"key":"ref53","article-title":"Laion-aesthetics","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref57","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref61","article-title":"Understanding diffusion models: A unified perspective","author":"Luo","year":"2022"},{"key":"ref62","article-title":"Text-to-image diffusion model in generative AI: A survey","author":"Zhang","year":"2023"},{"key":"ref63","article-title":"DreamArtist: Towards controllable one-shot text-to-image generation via contrastive prompt-tuning","author":"Dong","year":"2022"},{"key":"ref64","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref66","article-title":"$ p+$p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref68","article-title":"DIFFNAT: Improving diffusion image quality using natural image statistics","author":"Roy","year":"2023"},{"key":"ref69","article-title":"VideoAssembler: Identity-consistent video generation with reference entities using diffusion model","author":"Zhao","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_12"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref72","article-title":"An image is worth multiple words: Discovering object level concepts using multi-concept prompt learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Jin","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00802"},{"key":"ref74","article-title":"DreamDistribution: Learning prompt distribution for diverse in-distribution generation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Zhao","year":"2025"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531917"},{"key":"ref76","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref77","article-title":"LoRA Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.239"},{"key":"ref79","article-title":"One-for-all: Generalized lora for parameter-efficient fine-tuning","author":"Chavan","year":"2023"},{"key":"ref80","first-page":"38125","article-title":"COMCAT: Towards efficient compression and customization of attention-based vision models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao","year":"2023"},{"key":"ref81","article-title":"DisenBooth: Disentangled parameter-efficient tuning for subject-driven text-to-image generation","author":"Chen","year":"2023"},{"key":"ref82","first-page":"15890","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Gu","year":"2023"},{"key":"ref83","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with C-lora","author":"Smith","year":"2023"},{"key":"ref84","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00348"},{"key":"ref86","article-title":"A closer look at parameter-efficient tuning in diffusion models","author":"Xiang","year":"2023"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref88","article-title":"Navigating text-to-image customization: From lycoris fine-tuning to model evaluation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yeh","year":"2023"},{"key":"ref89","article-title":"ConsisLoRA: Enhancing content and style consistency for lora-based style transfer","author":"Chen","year":"2025"},{"key":"ref90","article-title":"MotionCrafter: One-shot motion customization of diffusion models","author":"Zhang","year":"2023"},{"key":"ref91","first-page":"66860","article-title":"StyleDrop text-to-image synthesis of any style","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Sohn","year":"2023"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27850"},{"key":"ref94","article-title":"Generate anything anywhere in any scene","author":"Li","year":"2023"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_7"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687642"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3506992"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28565"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28020"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00661"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3200"},{"key":"ref103","article-title":"An image is worth multiple words: Learning object level concepts using multi-concept prompt learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Jin","year":"2024"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687658"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00794"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00906"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref110","first-page":"79320","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Qiu","year":"2023"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref112","article-title":"HiFi Tuner: High-fidelity subject-driven fine-tuning for diffusion models","author":"Wang","year":"2023"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680894"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00689"},{"key":"ref115","first-page":"37491","article-title":"Is this loss informative? Faster text-to-image customization by tracking objective dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Voronov","year":"2023"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612599"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00590"},{"key":"ref118","article-title":"Controllable textual inversion for personalized text-to-image generation","author":"Yang","year":"2023"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00372"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680773"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00817"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00692"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00734"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1136"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00782"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_23"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33187"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00356"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687604"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref133","article-title":"Cocktail: Mixing multi-modality controls for text-conditional image generation","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Hu","year":"2023"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28024"},{"key":"ref135","first-page":"42961","article-title":"UniControl: A unified diffusion model for controllable visual generation in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Qin","year":"2023"},{"key":"ref136","article-title":"Meta controlnet: Enhancing task adaptation via meta learning","author":"Yang","year":"2023"},{"key":"ref137","first-page":"343","article-title":"Controlnet-xs: Designing an efficient and effective architecture for controlling text-to-image diffusion models","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zavadski","year":"2024"},{"key":"ref138","article-title":"CCM: Adding conditional controls to text-to-image consistency models","author":"Xiao","year":"2023"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00885"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32309"},{"key":"ref144","article-title":"Ctrl-Adapter: An efficient and versatile framework for adapting diverse controls to any diffusion model","volume-title":"Proc. 13th Int. Conf. Learn. Representations","volume":"2024","author":"Lin"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00838"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591549"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/icme59968.2025.11209238"},{"key":"ref153","article-title":"Layered rendering diffusion model for zero-shot guided image synthesis","author":"Qi","year":"2023"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00591"},{"key":"ref155","article-title":"Integrating geometric control into text-to-image diffusion models for high-quality detection data generation via text prompt","author":"Chen","year":"2023"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_9"},{"key":"ref157","article-title":"LayoutDiffuse: Adapting foundational diffusion models for layout-to-image generation","author":"Cheng","year":"2023"},{"key":"ref158","article-title":"Conditioning diffusion models via attributes and semantic masks for face generation","author":"Giambi","year":"2023"},{"key":"ref159","article-title":"JointNet: Extending text-to-image diffusion for dense distribution modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref160","article-title":"HyperHuman: Hyper-realistic human generation with latent structural diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_8"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00688"},{"key":"ref163","article-title":"Adversarial supervision makes layout-to-image diffusion models thrive","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2024"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657525"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_1"},{"key":"ref166","article-title":"Unified multi-modal latent diffusion for joint subject and text conditional image generation","author":"Ma","year":"2023"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618173"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref171","article-title":"Kosmos-G: Generating images in context with multimodal large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pan","year":"2024"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00714"},{"key":"ref174","article-title":"VSC: Visual search compositional text-to-image diffusion model","author":"Dat","year":"2025"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34264"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91907-7_15"},{"key":"ref177","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00877"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref183","article-title":"ViscoNet: Bridging and harmonizing visual and textual conditioning for controlnet","author":"Cheong","year":"2023"},{"key":"ref184","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27891"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00733"},{"key":"ref191","first-page":"36777","article-title":"PuLID: Pure and lightning ID customization via contrastive alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Guo","year":"2024"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687662"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00100"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00654"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00612"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_19"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00206"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00213"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_27"},{"key":"ref202","article-title":"LSAP: Rethinking inversion fidelity, perception and editability in GAN latent space","author":"Cao","year":"2022"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00419"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_2"},{"key":"ref205","article-title":"Stellar: Systematic evaluation of human-centric personalized text-to-image methods","author":"Achlioptas","year":"2023"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00829"},{"key":"ref209","first-page":"80220","article-title":"GenWarp: Single image to novel views with semantic-preserving generative warping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Seo","year":"2024"},{"key":"ref210","first-page":"7591","article-title":"Integrating view conditions for image synthesis","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Bai","year":"2024"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681396"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687564"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00266"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00738"},{"key":"ref217","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00608"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_6"},{"key":"ref221","article-title":"Improving in-context learning in diffusion models with visual context-modulated prompts","author":"Chen","year":"2023"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_22"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-42891-8"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1145\/3604078.3604160"},{"key":"ref227","article-title":"DreamDiffusion: Generating high-quality images from brain EEG signals","author":"Bai","year":"2023"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889805"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02539"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446362"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.900"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref233","article-title":"AnyText: Multilingual visual text generation and editing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tuo","year":"2024"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_13"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_21"},{"key":"ref237","first-page":"44050","article-title":"GlyphControl: Glyph conditional control for visual text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang","year":"2023"},{"key":"ref238","article-title":"LoCo: Locally constrained training-free layout-to-image synthesis","author":"Zhao","year":"2023"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00714"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890356"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref244","article-title":"Region-aware text-to-image generation via hard binding and soft refinement","author":"Chen","year":"2024"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_16"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28364"},{"key":"ref247","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":"2023"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref250","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Feng","year":"2023"},{"key":"ref251","first-page":"33602","article-title":"REFDrop: Controllable consistency in image or video generation via reference feature guidance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Fan","year":"2024"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_14"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00868"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1145\/3658136"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3101"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680658"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112111"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref260","article-title":"On mechanistic knowledge localization in text-to-image generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Basu","year":"2024"},{"key":"ref261","first-page":"1737","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bar-Tal","year":"2023"},{"key":"ref262","article-title":"Exploring position encoding in diffusion u-net for training-free high-resolution image generation","author":"Zhou","year":"2025"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref264","article-title":"Late-constraint diffusion guidance for controllable image synthesis","author":"Liu","year":"2023"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref268","article-title":"R&B: Region and boundary aware zero-shot grounded text-to-image generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao","year":"2023"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref270","article-title":"Adding additional control to one-step diffusion with joint distribution matching","author":"Luo","year":"2025"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33139"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32240"},{"key":"ref274","article-title":"MAGIC: Multi-modality guided image completion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2024"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00385"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01713"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref278","article-title":"Divide & bind your attention for improved generative semantic nursing","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Li","year":"2023"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_4"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref281","first-page":"13753","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2023"},{"key":"ref282","article-title":"UniCombine: Unified multi-conditional combination with diffusion transformer","author":"Wang","year":"2025"},{"key":"ref283","first-page":"29935","article-title":"Non-confusing generation of customized concepts in diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin","year":"2024"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_6"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00614"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3553024"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3382753"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00181"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00280"},{"key":"ref290","article-title":"Cones: Concept neurons in diffusion models for customized generation","author":"Liu","year":"2023"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00761"},{"key":"ref292","article-title":"Cones 2: Customizable image synthesis with multiple subjects","author":"Liu","year":"2023"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00848"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00733"},{"key":"ref296","first-page":"21","article-title":"Decompose and realign: Tackling condition misalignment in text-to-image diffusion models","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Wang","year":"2024"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00643"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_2"},{"key":"ref299","article-title":"DiffBlender: Scalable and composable multimodal text-to-image diffusion models","author":"Kim","year":"2023"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref302","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref308","article-title":"Towards accurate guided diffusion sampling through symplectic adjoint method","author":"Pan","year":"2023"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14966"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref311","article-title":"DreamInPainter: Text-guided subject-driven image inpainting with diffusion models","author":"Xie","year":"2023"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1145\/3658237"},{"key":"ref313","first-page":"8406","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3 d generation with variational score distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref315","article-title":"CameraCtrl: Enabling camera control for video diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2025"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref317","article-title":"Custom-Edit: Text-guided image editing with customized diffusion models","author":"Choi","year":"2023"},{"key":"ref318","article-title":"Multi-turn consistent image editing","author":"Zhou","year":"2025"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612200"},{"key":"ref320","article-title":"DreamCom: Finetuning text-guided inpainting model for image composition","author":"Lu","year":"2023"},{"key":"ref321","article-title":"ControlCom: Controllable image composition using diffusion model","author":"Zhang","year":"2023"},{"key":"ref322","article-title":"Dreamfusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Poole","year":"2022"},{"key":"ref323","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612489"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00513"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612232"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref328","article-title":"VD3D: Taming large video diffusion transformers for 3D camera control","author":"Bahmani","year":"2024"},{"key":"ref329","article-title":"EgoSim: Egocentric exploration in virtual worlds with multi-modal conditioning","volume-title":"Proc. Int. Conf. Learn. Representations, 2025","author":"Yu"},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"ref332","article-title":"ReCamMaster: Camera-controlled generative rendering from a single video","author":"Bai","year":"2025"},{"key":"ref333","article-title":"Training-free camera control for video generation","author":"Hou","year":"2024"},{"key":"ref334","article-title":"MotionClone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024"},{"key":"ref335","article-title":"WorldForge: Unlocking emergent 3D\/4D generation in video diffusion model via training-free guidance","author":"Song","year":"2025"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11304732.pdf?arnumber=11304732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:43Z","timestamp":1773106483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11304732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":336,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3646548","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":[[2026,4]]}}}