{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:19Z","timestamp":1784268379792,"version":"3.55.0"},"reference-count":35,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92470203,62472104"],"award-info":[{"award-number":["92470203,62472104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024XKRC082"],"award-info":[{"award-number":["2024XKRC082"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01490","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16058-16067","source":"Crossref","is-referenced-by-count":2,"title":["CharaConsist: Fine-Grained Consistent Character Generation"],"prefix":"10.1109","author":[{"given":"Mengyu","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Institute of Big Data, Fudan University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianing","family":"Peng","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunpeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Alkaid Pte. Ltd.,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref3","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML. OpenReview.net","author":"Esser","year":"2024"},{"key":"ref4","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"ICLR. OpenReview.net","author":"Gal","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref8","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref10","author":"Kong","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref12","volume-title":"Flux","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref14","author":"Li","year":"2024","journal-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51701.2025.01607","article-title":"AnyI2V: Animating any conditional image with motion control generation","volume-title":"ICCV","author":"Li","year":"2025"},{"key":"ref16","article-title":"One-prompt-one-story: Free-lunch consistent text-to-image generation using a single prompt","volume-title":"ICLR","author":"Liu","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref18","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR. OpenReview.net","author":"Podell","year":"2024"},{"key":"ref19","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":"140","key":"ref20","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref25","author":"Shuai","year":"2024","journal-title":"A survey of multimodal-guided image editing with text-to-image diffusion models"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01157"},{"key":"ref27","first-page":"22562265","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref29","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume":"36","author":"Tang","year":"2023","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","first-page":"54015","article-title":"Q-align: teaching 1 mms for visual scoring via discrete text-defined levels","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Wu","year":"2024"},{"key":"ref33","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref34","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref35","article-title":"Storydiffusion: Consistent selfattention for long-range image and video generation","volume-title":"NeurIPS","author":"Zhou","year":"2024"}],"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\/11445799.pdf?arnumber=11445799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:35Z","timestamp":1777529735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445799\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01490","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}