{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:12:01Z","timestamp":1761894721334,"version":"build-2065373602"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209506","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["CE-LoRA: Consistent Person Synthesis by Exploring the Model\u2019s Spatial Consistency"],"prefix":"10.1109","author":[{"given":"Delong","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Lei","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Su","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","year":"2021","author":"Nichol","key":"ref2"},{"volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","year":"2023","author":"Podell","key":"ref3"},{"key":"ref4","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Instantid: Zero-shot identity-preserving generation in seconds","year":"2024","author":"Wang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"journal-title":"Flashface: Human image personalization with high-fidelity identity preservation","year":"2024","author":"Zhang","key":"ref7"},{"journal-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","year":"2023","author":"Ye","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"journal-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","year":"2022","author":"Gal","key":"ref11"},{"journal-title":"Pulid: Pure and lightning id customization via contrastive alignment","year":"2024","author":"Guo","key":"ref12"},{"journal-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref13"},{"journal-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref14"},{"journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref15"},{"key":"ref16","article-title":"Generating images with multimodal language models","volume":"36","author":"Koh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Pandagpt: One model to instruction-follow them all","year":"2023","author":"Su","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","year":"2024","author":"Wang","key":"ref19"},{"year":"2024","key":"ref20","article-title":"Flux: Official inference repository for flux.1 models"},{"journal-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"article-title":"Qwen2.5: A party of foundation models","year":"2024","author":"Team","key":"ref23"},{"journal-title":"Retinaface: Single-stage dense face localisation in the wild","year":"2019","author":"Deng","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"journal-title":"Prodigy: An expeditiously adaptive parameter-free learner","year":"2023","author":"Mishchenko","key":"ref26"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"journal-title":"Dinov2: Learning robust visual features without supervision","year":"2023","author":"Oquab","key":"ref28"},{"year":"2024","key":"ref29","article-title":"Mediapipe: Cross-platform, customizable ml solutions for live and streaming media"},{"key":"ref30","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"year":"2024","key":"ref31","article-title":"flux-ip-adapter-v2"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209506.pdf?arnumber=11209506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:34:35Z","timestamp":1761888875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209506","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}