{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T23:04:10Z","timestamp":1784847850704,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,13]]},"DOI":"10.1145\/3641519.3657469","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T06:39:28Z","timestamp":1720766368000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":74,"title":["Subject-Diffusion: Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0057-3033","authenticated-orcid":false,"given":"Jian","family":"Ma","sequence":"first","affiliation":[{"name":"OPPO AI Center, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5612-7631","authenticated-orcid":false,"given":"Junhao","family":"Liang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3498-2527","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"OPPO AI Center, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6332-2785","authenticated-orcid":false,"given":"Haonan","family":"Lu","sequence":"additional","affiliation":[{"name":"OPPO AI Center, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"A Neural Space-Time Representation for Text-to-Image Personalization. arXiv preprint arXiv:2305.15391","author":"Alaluf Yuval","year":"2023","unstructured":"Yuval Alaluf, Elad Richardson, Gal Metzer, and Daniel Cohen-Or. 2023. A Neural Space-Time Representation for Text-to-Image Personalization. arXiv preprint arXiv:2305.15391 (2023)."},{"key":"e_1_3_2_2_2_1","volume-title":"Break-A-Scene: Extracting Multiple Concepts from a Single Image. arXiv preprint arXiv:2305.16311","author":"Avrahami Omri","year":"2023","unstructured":"Omri Avrahami, Kfir Aberman, Ohad Fried, Daniel Cohen-Or, and Dani Lischinski. 2023. Break-A-Scene: Extracting Multiple Concepts from a Single Image. arXiv preprint arXiv:2305.16311 (2023)."},{"key":"e_1_3_2_2_3_1","volume-title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324","author":"Balaji Yogesh","year":"2022","unstructured":"Yogesh Balaji, Seungjun Nah, Xun Huang, Arash Vahdat, Jiaming Song, Karsten Kreis, Miika Aittala, Timo Aila, Samuli Laine, Bryan Catanzaro, 2022. ediffi: Text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_2_7_1","volume-title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. arXiv preprint arXiv:2301.13826","author":"Chefer Hila","year":"2023","unstructured":"Hila Chefer, Yuval Alaluf, Yael Vinker, Lior Wolf, and Daniel Cohen-Or. 2023. Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. arXiv preprint arXiv:2301.13826 (2023)."},{"key":"e_1_3_2_2_8_1","volume-title":"Disenbooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation. arXiv preprint arXiv:2305.03374","author":"Chen Hong","year":"2023","unstructured":"Hong Chen, Yipeng Zhang, Xin Wang, Xuguang Duan, Yuwei Zhou, and Wenwu Zhu. 2023b. Disenbooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation. arXiv preprint arXiv:2305.03374 (2023)."},{"key":"e_1_3_2_2_9_1","volume-title":"PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models. arXiv preprint arXiv:2309.05793","author":"Chen Li","year":"2023","unstructured":"Li Chen, Mengyi Zhao, Yiheng Liu, Mingxu Ding, Yangyang Song, Shizun Wang, Xu Wang, Hao Yang, Jing Liu, Kang Du, 2023c. PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models. arXiv preprint arXiv:2309.05793 (2023)."},{"key":"e_1_3_2_2_10_1","volume-title":"Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186","author":"Chen Wenhu","year":"2023","unstructured":"Wenhu Chen, Hexiang Hu, Yandong Li, Nataniel Rui, Xuhui Jia, Ming-Wei Chang, and William\u00a0W Cohen. 2023a. Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186 (2023)."},{"key":"e_1_3_2_2_11_1","volume-title":"Re-imagen: Retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491","author":"Chen Wenhu","year":"2022","unstructured":"Wenhu Chen, Hexiang Hu, Chitwan Saharia, and William\u00a0W Cohen. 2022. Re-imagen: Retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491 (2022)."},{"key":"e_1_3_2_2_12_1","volume-title":"Gradient-Free Textual Inversion. arXiv preprint arXiv:2304.05818","author":"Fei Zhengcong","year":"2023","unstructured":"Zhengcong Fei, Mingyuan Fan, and Junshi Huang. 2023. Gradient-Free Textual Inversion. arXiv preprint arXiv:2304.05818 (2023)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"e_1_3_2_2_14_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit\u00a0H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_2_15_1","volume-title":"Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models. arXiv preprint arXiv:2305.18292","author":"Gu Yuchao","year":"2023","unstructured":"Yuchao Gu, Xintao Wang, Jay\u00a0Zhangjie Wu, Yujun Shi, Yunpeng Chen, Zihan Fan, Wuyou Xiao, Rui Zhao, Shuning Chang, Weijia Wu, 2023. Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models. arXiv preprint arXiv:2305.18292 (2023)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"e_1_3_2_2_17_1","volume-title":"Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion. arXiv preprint arXiv:2303.08767","author":"Han Inhwa","year":"2023","unstructured":"Inhwa Han, Serin Yang, Taesung Kwon, and Jong\u00a0Chul Ye. 2023b. Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion. arXiv preprint arXiv:2303.08767 (2023)."},{"key":"e_1_3_2_2_18_1","volume-title":"Svdiff: Compact parameter space for diffusion fine-tuning. arXiv preprint arXiv:2303.11305","author":"Han Ligong","year":"2023","unstructured":"Ligong Han, Yinxiao Li, Han Zhang, Peyman Milanfar, Dimitris Metaxas, and Feng Yang. 2023a. Svdiff: Compact parameter space for diffusion fine-tuning. arXiv preprint arXiv:2303.11305 (2023)."},{"key":"e_1_3_2_2_19_1","volume-title":"ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation. arXiv preprint arXiv:2306.00971","author":"Hao Shaozhe","year":"2023","unstructured":"Shaozhe Hao, Kai Han, Shihao Zhao, and Kwan-Yee\u00a0K Wong. 2023. ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation. arXiv preprint arXiv:2306.00971 (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)."},{"key":"e_1_3_2_2_21_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33 (2020), 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_22_1","unstructured":"Matthew Honnibal Ines Montani Sofie Van\u00a0Landeghem Adriane Boyd 2020. spaCy: Industrial-strength natural language processing in python. (2020)."},{"key":"e_1_3_2_2_23_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu J","year":"2021","unstructured":"Edward\u00a0J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_2_24_1","unstructured":"Junha Hyung Jaeyo Shin and Jaegul Choo. 2023. MagiCapture: High-Resolution Multi-Concept Portrait Customization. arxiv:2309.06895\u00a0[cs.CV]"},{"key":"e_1_3_2_2_25_1","volume-title":"Taming encoder for zero fine-tuning image customization with text-to-image diffusion models. arXiv preprint arXiv:2304.02642","author":"Jia Xuhui","year":"2023","unstructured":"Xuhui Jia, Yang Zhao, Kelvin\u00a0CK Chan, Yandong Li, Han Zhang, Boqing Gong, Tingbo Hou, Huisheng Wang, and Yu-Chuan Su. 2023. Taming encoder for zero fine-tuning image customization with text-to-image diffusion models. arXiv preprint arXiv:2304.02642 (2023)."},{"key":"e_1_3_2_2_26_1","volume-title":"Segment anything. arXiv preprint arXiv:2304.02643","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander\u00a0C Berg, Wan-Yen Lo, 2023. Segment anything. arXiv preprint arXiv:2304.02643 (2023)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_2_30_1","volume-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. arXiv preprint arXiv:2305.14720","author":"Li Dongxu","year":"2023","unstructured":"Dongxu Li, Junnan Li, and Steven\u00a0CH Hoi. 2023a. Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. arXiv preprint arXiv:2305.14720 (2023)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_2_32_1","volume-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499","author":"Liu Shilong","year":"2023","unstructured":"Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, 2023a. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_2_33_1","volume-title":"Cones 2: Customizable Image Synthesis with Multiple Subjects. arXiv preprint arXiv:2305.19327","author":"Liu Zhiheng","year":"2023","unstructured":"Zhiheng Liu, Yifei Zhang, Yujun Shen, Kecheng Zheng, Kai Zhu, Ruili Feng, Yu Liu, Deli Zhao, Jingren Zhou, and Yang Cao. 2023b. Cones 2: Customizable Image Synthesis with Multiple Subjects. arXiv preprint arXiv:2305.19327 (2023)."},{"key":"e_1_3_2_2_34_1","volume-title":"GlyphDraw: Learning to Draw Chinese Characters in Image Synthesis Models Coherently. arXiv preprint arXiv:2303.17870","author":"Ma Jian","year":"2023","unstructured":"Jian Ma, Mingjun Zhao, Chen Chen, Ruichen Wang, Di Niu, Haonan Lu, and Xiaodong Lin. 2023b. GlyphDraw: Learning to Draw Chinese Characters in Image Synthesis Models Coherently. arXiv preprint arXiv:2303.17870 (2023)."},{"key":"e_1_3_2_2_35_1","volume-title":"Unified multi-modal latent diffusion for joint subject and text conditional image generation. arXiv preprint arXiv:2303.09319","author":"Ma Yiyang","year":"2023","unstructured":"Yiyang Ma, Huan Yang, Wenjing Wang, Jianlong Fu, and Jiaying Liu. 2023a. Unified multi-modal latent diffusion for joint subject and text conditional image generation. arXiv preprint arXiv:2303.09319 (2023)."},{"key":"e_1_3_2_2_36_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning. PMLR, 16784\u201316804","author":"Nichol Alexander\u00a0Quinn","year":"2022","unstructured":"Alexander\u00a0Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob Mcgrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning. PMLR, 16784\u201316804."},{"key":"e_1_3_2_2_37_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_2_38_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)."},{"key":"e_1_3_2_2_39_1","volume-title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment. arXiv preprint arXiv:2306.08877","author":"Rassin Royi","year":"2023","unstructured":"Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, and Gal Chechik. 2023. Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment. arXiv preprint arXiv:2306.08877 (2023)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_2_42_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily\u00a0L Denton, Kamyar Ghasemipour, Raphael Gontijo\u00a0Lopes, Burcu Karagol\u00a0Ayan, Tim Salimans, 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems 35 (2022), 36479\u201336494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_43_1","volume-title":"Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022)."},{"key":"e_1_3_2_2_44_1","volume-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114","author":"Schuhmann Christoph","year":"2021","unstructured":"Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)."},{"key":"e_1_3_2_2_45_1","volume-title":"Instantbooth: Personalized text-to-image generation without test-time finetuning. arXiv preprint arXiv:2304.03411","author":"Shi Jing","year":"2023","unstructured":"Jing Shi, Wei Xiong, Zhe Lin, and Hyun\u00a0Joon Jung. 2023. Instantbooth: Personalized text-to-image generation without test-time finetuning. arXiv preprint arXiv:2304.03411 (2023)."},{"key":"e_1_3_2_2_46_1","volume-title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora. arXiv preprint arXiv:2304.06027","author":"Smith James\u00a0Seale","year":"2023","unstructured":"James\u00a0Seale Smith, Yen-Chang Hsu, Lingyu Zhang, Ting Hua, Zsolt Kira, Yilin Shen, and Hongxia Jin. 2023. Continual diffusion: Continual customization of text-to-image diffusion with c-lora. arXiv preprint arXiv:2304.06027 (2023)."},{"key":"e_1_3_2_2_47_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020a. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_2_48_1","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song Yang","year":"2020","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik\u00a0P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020b. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)."},{"key":"e_1_3_2_2_49_1","volume-title":"Key-locked rank one editing for text-to-image personalization. arXiv preprint arXiv:2305.01644","author":"Tewel Yoad","year":"2023","unstructured":"Yoad Tewel, Rinon Gal, Gal Chechik, and Yuval Atzmon. 2023. Key-locked rank one editing for text-to-image personalization. arXiv preprint arXiv:2305.01644 (2023)."},{"key":"e_1_3_2_2_50_1","volume-title":"Extended Textual Conditioning in Text-to-Image Generation. arXiv preprint arXiv:2303.09522","author":"Voynov Andrey","year":"2023","unstructured":"Andrey Voynov, Qinghao Chu, Daniel Cohen-Or, and Kfir Aberman. 2023. P + : Extended Textual Conditioning in Text-to-Image Generation. arXiv preprint arXiv:2303.09522 (2023)."},{"key":"e_1_3_2_2_51_1","volume-title":"Compositional text-to-image synthesis with attention map control of diffusion models. arXiv preprint arXiv:2305.13921","author":"Wang Ruichen","year":"2023","unstructured":"Ruichen Wang, Zekang Chen, Chen Chen, Jian Ma, Haonan Lu, and Xiaodong Lin. 2023a. Compositional text-to-image synthesis with attention map control of diffusion models. arXiv preprint arXiv:2305.13921 (2023)."},{"key":"e_1_3_2_2_52_1","unstructured":"Yibin Wang Weizhong Zhang Jianwei Zheng and Cheng Jin. 2023b. High-fidelity Person-centric Subject-to-Image Synthesis. arxiv:2311.10329\u00a0[cs.CV]"},{"key":"e_1_3_2_2_53_1","volume-title":"Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848","author":"Wei Yuxiang","year":"2023","unstructured":"Yuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, and Wangmeng Zuo. 2023. Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848 (2023)."},{"key":"e_1_3_2_2_54_1","volume-title":"Harnessing the spatial-temporal attention of diffusion models for high-fidelity text-to-image synthesis. arXiv preprint arXiv:2304.03869","author":"Wu Qiucheng","year":"2023","unstructured":"Qiucheng Wu, Yujian Liu, Handong Zhao, Trung Bui, Zhe Lin, Yang Zhang, and Shiyu Chang. 2023. Harnessing the spatial-temporal attention of diffusion models for high-fidelity text-to-image synthesis. arXiv preprint arXiv:2304.03869 (2023)."},{"key":"e_1_3_2_2_55_1","volume-title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention. arXiv preprint arXiv:2305.10431","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Tianwei Yin, William\u00a0T Freeman, Fr\u00e9do Durand, and Song Han. 2023. FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention. arXiv preprint arXiv:2305.10431 (2023)."},{"key":"e_1_3_2_2_56_1","volume-title":"Controllable Textual Inversion for Personalized Text-to-Image Generation. arXiv preprint arXiv:2304.05265","author":"Yang Jianan","year":"2023","unstructured":"Jianan Yang, Haobo Wang, Ruixuan Xiao, Sai Wu, Gang Chen, and Junbo Zhao. 2023. Controllable Textual Inversion for Personalized Text-to-Image Generation. arXiv preprint arXiv:2304.05265 (2023)."},{"key":"e_1_3_2_2_57_1","unstructured":"Hu Ye Jun Zhang Sibo Liu Xiao Han and Wei Yang. 2023. IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models. arxiv:2308.06721\u00a0[cs.CV]"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"e_1_3_2_2_59_1","unstructured":"Yufan Zhou Ruiyi Zhang Jiuxiang Gu and Tong Sun. 2023a. Customization Assistant for Text-to-image Generation. arxiv:2312.03045\u00a0[cs.CV]"},{"key":"e_1_3_2_2_60_1","volume-title":"Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach. arXiv preprint arXiv:2305.13579","author":"Zhou Yufan","year":"2023","unstructured":"Yufan Zhou, Ruiyi Zhang, Tong Sun, and Jinhui Xu. 2023b. Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach. arXiv preprint arXiv:2305.13579 (2023)."}],"event":{"name":"SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Denver CO USA","acronym":"SIGGRAPH '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657469","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:16:19Z","timestamp":1755890179000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657469"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":60,"alternative-id":["10.1145\/3641519.3657469","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657469","relation":{},"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"2024-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}