{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:00:58Z","timestamp":1765310458775,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406126"],"award-info":[{"award-number":["62406126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Project of the Education Department of Jilin Province","award":["JJKH20250119KJ"],"award-info":[{"award-number":["JJKH20250119KJ"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755174","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:39:06Z","timestamp":1761377946000},"page":"7854-7863","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0829-6267","authenticated-orcid":false,"given":"Ruoxuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4665-6978","authenticated-orcid":false,"given":"Bin","family":"Wen","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5652-4327","authenticated-orcid":false,"given":"Hongxia","family":"Xie","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8227-5662","authenticated-orcid":false,"given":"Yi","family":"Yao","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5178-752X","authenticated-orcid":false,"given":"Songhan","family":"Zuo","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5739-4228","authenticated-orcid":false,"given":"Jian-Yu","family":"Jiang-Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2216-077X","authenticated-orcid":false,"given":"Hong-Han","family":"Shuai","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4662-7875","authenticated-orcid":false,"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_4_1","volume-title":"Training-free regional prompting for diffusion transformers. arXiv preprint arXiv:2411.02395","author":"Chen Anthony","year":"2024","unstructured":"Anthony Chen, Jianjin Xu, Wenzhao Zheng, Gaole Dai, Yida Wang, Renrui Zhang, Haofan Wang, and Shanghang Zhang. 2024. Training-free regional prompting for diffusion transformers. arXiv preprint arXiv:2411.02395 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680621"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680977"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093463"},{"key":"e_1_3_2_1_9_1","volume-title":"In-context lora for diffusion transformers. arXiv preprint arXiv:2410.23775","author":"Huang Lianghua","year":"2024","unstructured":"Lianghua Huang, Wei Wang, Zhi-Fan Wu, Yupeng Shi, Huanzhang Dou, Chen Liang, Yutong Feng, Yu Liu, and Jingren Zhou. 2024. In-context lora for diffusion transformers. arXiv preprint arXiv:2410.23775 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2929447"},{"key":"e_1_3_2_1_11_1","unstructured":"Black Forest Labs. 2024. Flux.1 AI. https:\/\/flux1ai.com\/. Accessed: 2025-04-04."},{"key":"e_1_3_2_1_12_1","volume-title":"Foodsam: Any food segmentation","author":"Lan Xing","year":"2023","unstructured":"Xing Lan, Jiayi Lyu, Hanyu Jiang, Kun Dong, Zehai Niu, Yi Zhang, and Jian Xue. 2023. Foodsam: Any food segmentation. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3554738"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_5"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-2407"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2927476"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00600"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414031"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413765"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413765"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413636"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"e_1_3_2_1_26_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612012"},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_29_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1-67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_33_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_34_1","unstructured":"Stability AI. 2022. Stable Diffusion v2.1 Model Card. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-2-1. Accessed: 2025-04-11."},{"key":"e_1_3_2_1_35_1","unstructured":"Stability AI. 2024. Stable Diffusion 3.5 Large Model Card. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-3.5-large. Accessed: 2025-04-11."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475422"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00879"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3684997"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475201"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549203"},{"key":"e_1_3_2_1_41_1","volume-title":"Visual Goal-Step Inference using wikiHow. arXiv preprint arXiv:2104.05845","author":"Yang Yue","year":"2021","unstructured":"Yue Yang, Artemis Panagopoulou, Qing Lyu, Li Zhang, Mark Yatskar, and Chris Callison-Burch. 2021. Visual Goal-Step Inference using wikiHow. arXiv preprint arXiv:2104.05845 (2021)."},{"key":"e_1_3_2_1_42_1","volume-title":"Foodlmm: A versatile food assistant using large multi-modal model. arXiv preprint arXiv:2312.14991","author":"Yin Yuehao","year":"2023","unstructured":"Yuehao Yin, Huiyan Qi, Bin Zhu, Jingjing Chen, Yu-Gang Jiang, and Chong-Wah Ngo. 2023. Foodlmm: A versatile food assistant using large multi-modal model. arXiv preprint arXiv:2312.14991 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350608"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01297-w"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-025-01809-2"},{"key":"e_1_3_2_1_46_1","volume-title":"RecipeGen: A Benchmark for Real-World Recipe Image Generation. arXiv preprint arXiv:2503.05228","author":"Zhang Ruoxuan","year":"2025","unstructured":"Ruoxuan Zhang, Hongxia Xie, Yi Yao, Jian-Yu Jiang-Lin, Bin Wen, Ling Lo, Hong-Han Shuai, Yung-Hui Li, and Wen-Huang Cheng. 2025b. RecipeGen: A Benchmark for Real-World Recipe Image Generation. arXiv preprint arXiv:2503.05228 (2025)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552485.3554938"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"e_1_3_2_1_49_1","volume-title":"FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination. arXiv preprint arXiv:2406.10261","author":"Zhou Pengfei","year":"2024","unstructured":"Pengfei Zhou, Weiqing Min, Chaoran Fu, Ying Jin, Mingyu Huang, Xiangyang Li, Shuhuan Mei, and Shuqiang Jiang. 2024a. FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination. arXiv preprint arXiv:2406.10261 (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612661"},{"key":"e_1_3_2_1_51_1","first-page":"110315","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","volume":"37","author":"Zhou Yupeng","year":"2024","unstructured":"Yupeng Zhou, Daquan Zhou, Ming-Ming Cheng, Jiashi Feng, and Qibin Hou. 2024b. Storydiffusion: Consistent self-attention for long-range image and video generation. Advances in Neural Information Processing Systems, Vol. 37 (2024), 110315-110340.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:58:47Z","timestamp":1765310327000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755174"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3755174","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755174","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}