{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:44:12Z","timestamp":1769546652726,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,7]]},"DOI":"10.1145\/3779153.3779165","type":"proceedings-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T07:35:51Z","timestamp":1769499351000},"page":"77-82","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompt-Faithful and Identity-Consistent Generation via Serial Cross-Attention Diffusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2450-4741","authenticated-orcid":false,"given":"Xuyuan","family":"Liu","sequence":"first","affiliation":[{"name":"Chongqing Key Laboratory of Intelligent Sensing and Blockchain Technology, School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3922-3319","authenticated-orcid":false,"given":"Xiping","family":"He","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Intelligent Sensing and Blockchain Technology, School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8225-7917","authenticated-orcid":false,"given":"Yi","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Intelligent Sensing and Blockchain Technology, School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1834-9716","authenticated-orcid":false,"given":"Ting","family":"Xiong","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Intelligent Sensing and Blockchain Technology, School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2111-0811","authenticated-orcid":false,"given":"Xiaoqin","family":"Xie","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Intelligent Sensing and Blockchain Technology, School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, Chongqing, China"}]}],"member":"320","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"e_1_3_3_1_1_2","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion[J]. arXiv preprint arXiv:2208.01618","author":"Gal R","year":"2022","unstructured":"Gal R, Alaluf Y, Atzmon Y, et al. An image is worth one word: Personalizing text-to-image generation using textual inversion[J]. arXiv preprint arXiv:2208.01618, 2022."},{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Ruiz N Li Y Jampani V et al. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023: 22500-22510.","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Arar M Gal R Atzmon Y et al. Domain-agnostic tuning-encoder for fast personalization of text-to-image models[C]\/\/SIGGRAPH Asia 2023 Conference Papers. 2023: 1-10.","DOI":"10.1145\/3610548.3618173"},{"key":"e_1_3_3_1_4_2","first-page":"1281","volume":"2024","author":"Chen Z","unstructured":"Chen Z, Fang S, Liu W, et al. DreamIdentity: enhanced editability for efficient face-identity preserved image generation[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(2): 1281-1289..","journal-title":"DreamIdentity: enhanced editability for efficient face-identity preserved image generation[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_3_1_5_2","volume-title":"Inserting anybody in diffusion models via celeb basis[J]. arXiv preprint arXiv:2306.00926","author":"Yuan G","year":"2023","unstructured":"Yuan G, Cun X, Zhang Y, et al. Inserting anybody in diffusion models via celeb basis[J]. arXiv preprint arXiv:2306.00926, 2023."},{"key":"e_1_3_3_1_6_2","volume-title":"Masterweaver: Taming editability and face identity for personalized text-to-image generation[C]\/\/European Conference on Computer Vision","author":"Wei Y","year":"2024","unstructured":"Wei Y, Ji Z, Bai J, et al. Masterweaver: Taming editability and face identity for personalized text-to-image generation[C]\/\/European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024: 252-271."},{"key":"e_1_3_3_1_7_2","first-page":"2187","volume":"2024","author":"Li X","unstructured":"Li X, Hou X, Loy C C. When stylegan meets stable diffusion: a w+ adapter for personalized image generation[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2024: 2187-2196.","journal-title":"Pattern Recognition."},{"key":"e_1_3_3_1_8_2","first-page":"10684","volume":"2022","author":"Rombach R","unstructured":"Rombach R, Blattmann A, Lorenz D, et al. High-resolution image synthesis with latent diffusion models[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022: 10684-10695.","journal-title":"High-resolution image synthesis with latent diffusion models[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition."},{"key":"e_1_3_3_1_9_2","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models[J]. arXiv preprint arXiv:2308.06721","author":"Ye H","year":"2023","unstructured":"Ye H, Zhang J, Liu S, et al. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models[J]. arXiv preprint arXiv:2308.06721, 2023."},{"key":"e_1_3_3_1_10_2","volume-title":"Progressive growing of gans for improved quality, stability, and variation, arXiv preprint arXiv:1710.10196","author":"Karras T.","year":"2017","unstructured":"Karras, T. Aila, S. Laine, J. Lehtinen, Progressive growing of gans for improved quality, stability, and variation, arXiv preprint arXiv:1710.10196 (2017)."},{"key":"e_1_3_3_1_11_2","first-page":"1","volume":"2024","author":"Xiao G","unstructured":"Xiao G, Yin T, Freeman W T, et al. Fastcomposer: Tuning-free multi-subject image generation with localized attention[J]. International Journal of Computer Vision, 2024: 1-20.","journal-title":"Fastcomposer: Tuning-free multi-subject image generation with localized attention[J]. International Journal of Computer Vision"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Li Z Cao M Wang X et al. Photomaker: Customizing realistic human photos via stacked id embedding[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2024: 8640-8650","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"e_1_3_3_1_13_2","first-page":"8748","volume":"2021","author":"Radford A","unstructured":"Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision[C]\/\/International conference on machine learning. PmLR, 2021: 8748-8763.","journal-title":"PmLR"},{"key":"e_1_3_3_1_14_2","first-page":"9650","volume":"2021","author":"Caron M","unstructured":"Caron M, Touvron H, Misra I, et al. Emerging properties in self-supervised vision transformers[C]\/\/Proceedings of the IEEE\/CVF international conference on computer vision. 2021: 9650-9660.","journal-title":"Emerging properties in self-supervised vision transformers[C]\/\/Proceedings of the IEEE\/CVF international conference on computer vision."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Deng J Guo J Xue N et al. Arcface: Additive angular margin loss for deep face recognition[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 4690-4699.","DOI":"10.1109\/CVPR.2019.00482"}],"event":{"name":"BDIOT 2025: 2025 9th International Conference on Big Data and Internet of Things","location":"Chongqing China","acronym":"BDIOT 2025"},"container-title":["Proceedings of the 2025 9th International Conference on Big Data and Internet of Things"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3779153.3779165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T07:36:55Z","timestamp":1769499415000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779153.3779165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":15,"alternative-id":["10.1145\/3779153.3779165","10.1145\/3779153"],"URL":"https:\/\/doi.org\/10.1145\/3779153.3779165","relation":{},"subject":[],"published":{"date-parts":[[2025,11,7]]},"assertion":[{"value":"2026-01-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}