{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T20:06:39Z","timestamp":1779739599733,"version":"3.53.1"},"reference-count":80,"publisher":"Tsinghua University Press","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.26599\/cvm.2025.9450462","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T19:52:22Z","timestamp":1776455542000},"page":"743-763","source":"Crossref","is-referenced-by-count":6,"title":["StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing"],"prefix":"10.26599","volume":"12","author":[{"given":"Senmao","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science, Nankai University,Tianjin,China,300350"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joost","family":"Van De Weijer","sequence":"additional","affiliation":[{"name":"The Computer Vision Center, Universitat Autònoma de Barcelona,Barcelona,Spain,08193"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taihang","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University,Tianjin,China,300350"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE,20015"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University,Tianjin,China,300350"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaxing","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University,Tianjin,China,300350"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University,Tianjin,China,300350"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University,Tianjin,China,300350"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref4","article-title":"StyleGAN-T: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Sauer","year":"2023"},{"key":"ref5","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00701"},{"key":"ref12","article-title":"MagicVideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"DreamFusion: Text-to-3D using 2D diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref15","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3D generation with variational score distillation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-301"},{"key":"ref19","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Accelerating diffusion models for inverse problems through shortcut sampling","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00585"},{"key":"ref24","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref26","article-title":"Highly personalized text embedding for image manipulation by stable diffusion","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref28","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"arXiv preprint","author":"Meng","year":"2108"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref30","article-title":"Adding conditional control to textto-image diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00192"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00390"},{"key":"ref37","article-title":"Memory replay GANs: Learning to generate new categories without forgetting","volume-title":"Proceedings of the 32nd Conference on Neural Information Processing Systems","author":"Wu","year":"2018"},{"key":"ref38","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref43","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proceedings of the 34th Conference on Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref44","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st Conference on Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref47","article-title":"DragonDiffusion: Enabling drag-style manipulation on diffusion models","author":"Mou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Taming encoder for zero fine-tuning image customization with text-to-image diffusion models","author":"Jia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14966"},{"key":"ref50","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","author":"Qiu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Differential diffusion: Giving each pixel its strength","author":"Levin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Re-imagine the negative prompt algorithm: Transform 2D diffusion into 3D, alleviate Janus problem and beyond","author":"Armandpour","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref54","article-title":"Diffusion models already have a semantic latent space","author":"Kwon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00526"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2875194"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00584"},{"key":"ref59","article-title":"On the \u201csteerability\u201d of generative adversarial networks","author":"Jahanian","year":"2020","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Precise recovery of latent vectors from generative adversarial networks","author":"Lipton","year":"2017","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181070"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.728"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00232"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"ref70","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Dhariwal","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref73","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"ADAM: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00207"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00424"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11534440\/11486268.pdf?arnumber=11486268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:53:11Z","timestamp":1779738791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11486268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":80,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450462","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}