{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:20:30Z","timestamp":1765340430263,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754942","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"9519-9528","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AnyStyleDiffusion: Flexible Style Transfer with Consistent Content Adaptation Across Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5779-5179","authenticated-orcid":false,"given":"Zhenyu","family":"Xu","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6190-5820","authenticated-orcid":false,"given":"Junjie","family":"Wu","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2741-3486","authenticated-orcid":false,"given":"Zhiyan","family":"Piao","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2929-5805","authenticated-orcid":false,"given":"Xiaoqi","family":"Sheng","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0230-6752","authenticated-orcid":false,"given":"Yu","family":"Xiao","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5000-2483","authenticated-orcid":false,"given":"Xinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"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":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In IEEE International Conference on Computer Vision.","author":"Bain Max","year":"2021","unstructured":"Max Bain, Arsha Nagrani, G\u00fcl Varol, and Andrew Zisserman. 2021. Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In IEEE International Conference on Computer Vision."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.296"},{"key":"e_1_3_2_1_3_1","volume-title":"Exploring low-dimensional subspace in diffusion models for controllable image editing. Advances in neural information processing systems","author":"Chen Siyi","year":"2024","unstructured":"Siyi Chen, Huijie Zhang, Minzhe Guo, Yifu Lu, Peng Wang, and Qing Qu. 2024. Exploring low-dimensional subspace in diffusion models for controllable image editing. Advances in neural information processing systems, Vol. 37 (2024), 27340-27371."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"e_1_3_2_1_5_1","unstructured":"Civitai. 2024. Civitai. https:\/\/civitai.com\/"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00662"},{"key":"e_1_3_2_1_7_1","volume-title":"Cogview: Mastering text-to-image generation via transformers. Advances in neural information processing systems","author":"Ding Ming","year":"2021","unstructured":"Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, et al., 2021. Cogview: Mastering text-to-image generation via transformers. Advances in neural information processing systems, Vol. 34 (2021), 19822-19835."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Ziyi Dong Pengxu Wei and Liang Lin. 2025. DreamArtist: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter. arXiv:2211.11337 [cs.CV] https:\/\/arxiv.org\/abs\/2211.11337","DOI":"10.1007\/s11263-025-02526-z"},{"key":"e_1_3_2_1_9_1","volume-title":"Forty-first international conference on machine learning.","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et al., 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning."},{"volume-title":"Two-Frame Motion Estimation Based on Polynomial Expansion","author":"Farneb\u00e4ck Gunnar","key":"e_1_3_2_1_10_1","unstructured":"Gunnar Farneb\u00e4ck. 2003. Two-Frame Motion Estimation Based on Polynomial Expansion. In Image Analysis, Josef Bigun and Tomas Gustavsson (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 363-370."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit H. Bermano Gal Chechik and Daniel Cohen-Or. 2022. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. doi:10.48550\/ARXIV.2208.01618","DOI":"10.48550\/ARXIV.2208.01618"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_15_1","volume-title":"Exploring the structure of a real-time, arbitrary neural artistic stylization network. arXiv preprint arXiv:1705.06830","author":"Ghiasi Golnaz","year":"2017","unstructured":"Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin, and Jonathon Shlens. 2017. Exploring the structure of a real-time, arbitrary neural artistic stylization network. arXiv preprint arXiv:1705.06830 (2017)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00721"},{"key":"e_1_3_2_1_17_1","unstructured":"Yuwei Guo Ceyuan Yang Anyi Rao Zhengyang Liang Yaohui Wang Yu Qiao Maneesh Agrawala Dahua Lin and Bo Dai. 2023. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning."},{"key":"e_1_3_2_1_18_1","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium (NIPS'17). Curran Associates Inc., Red Hook","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local nash equilibrium (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 6629-6640.","journal-title":"NY, USA"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496298"},{"key":"e_1_3_2_1_20_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020b. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_21_1","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arXiv:2207.12598 [cs.LG] https:\/\/arxiv.org\/abs\/2207.12598"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00591"},{"key":"e_1_3_2_1_23_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J 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_1_24_1","volume-title":"Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi.","author":"Ilharco Gabriel","year":"2022","unstructured":"Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2022. Editing models with task arithmetic. arXiv preprint arXiv:2212.04089 (2022)."},{"key":"e_1_3_2_1_25_1","unstructured":"Andrej Karpathy. 2022. Stable Diffusion Walk. https:\/\/gist.github.com\/karpathy\/00103b0037c5aaea32fe1da1af553355"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Nupur Kumari Bingliang Zhang Richard Zhang Eli Shechtman and Jun-Yan Zhu. 2023a. Multi-Concept Customization of Text-to-Image Diffusion. (2023).","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_1_27_1","first-page":"1931","article-title":"Multi-concept customization of text-to-image diffusion","author":"Kumari Nupur","year":"2023","unstructured":"Nupur Kumari, Bingliang Zhang, Richard Zhang, Eli Shechtman, and Jun-Yan Zhu. 2023b. Multi-concept customization of text-to-image diffusion. In CVPR. 1931-1941.","journal-title":"CVPR."},{"key":"e_1_3_2_1_28_1","volume-title":"Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960","author":"Kwon Mingi","year":"2022","unstructured":"Mingi Kwon, Jaeseok Jeong, and Youngjung Uh. 2022. Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960 (2022)."},{"key":"e_1_3_2_1_29_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_1_30_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Li Dongxu","year":"2024","unstructured":"Dongxu Li, Junnan Li, and Steven Hoi. 2024. Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"volume-title":"ControlNet: Improving Conditional Controls with Efficient Consistency Feedback","author":"Li Ming","key":"e_1_3_2_1_32_1","unstructured":"Ming Li, Taojiannan Yang, Huafeng Kuang, Jie Wu, Zhaoning Wang, Xuefeng Xiao, and Chen Chen. 2025. ControlNet: Improving Conditional Controls with Efficient Consistency Feedback. In ECCV. Springer, 129-147."},{"key":"e_1_3_2_1_33_1","first-page":"115712","article-title":"Schedule your edit: A simple yet effective diffusion noise schedule for image editing","volume":"37","author":"Lin Haonan","year":"2024","unstructured":"Haonan Lin, Yan Chen, Jiahao Wang, Wenbin An, Mengmeng Wang, Feng Tian, Yong Liu, Guang Dai, Jingdong Wang, and Qianying Wang. 2024. Schedule your edit: A simple yet effective diffusion noise schedule for image editing. Advances in Neural Information Processing Systems, Vol. 37 (2024), 115712-115756.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_1_35_1","volume-title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation. arXiv preprint arXiv:2407.02371","author":"Nan Kepan","year":"2024","unstructured":"Kepan Nan, Rui Xie, Penghao Zhou, Tiehan Fan, Zhenheng Yang, Zhijie Chen, Xiang Li, Jian Yang, and Ying Tai. 2024. OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation. arXiv preprint arXiv:2407.02371 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV] https:\/\/arxiv.org\/abs\/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:2307.01952 [cs.CV] https:\/\/arxiv.org\/abs\/2307.01952"},{"key":"e_1_3_2_1_37_1","first-page":"8693","article-title":"DEADiff","author":"Qi Tianhao","year":"2024","unstructured":"Tianhao Qi, Shancheng Fang, Yanze Wu, Hongtao Xie, Jiawei Liu, Lang Chen, Qian He, and Yongdong Zhang. 2024. DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations. In CVPR. 8693-8702.","journal-title":"An Efficient Stylization Diffusion Model with Disentangled Representations. In CVPR."},{"key":"e_1_3_2_1_38_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., 2021a. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_39_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., 2021b. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_40_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, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_41_1","volume-title":"International conference on machine learning. Pmlr, 8821-8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International conference on machine learning. Pmlr, 8821-8831."},{"key":"e_1_3_2_1_42_1","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models. CoRR","author":"Rombach Robin","year":"2021","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. CoRR, Vol. abs\/2112.10752 (2021). arXiv:2112.10752 https:\/\/arxiv.org\/abs\/2112.10752"},{"key":"e_1_3_2_1_43_1","first-page":"22500","article-title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","author":"Ruiz Nataniel","year":"2023","unstructured":"Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2023. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In CVPR. 22500-22510.","journal-title":"CVPR."},{"key":"e_1_3_2_1_44_1","first-page":"6527","article-title":"Hyperdreambooth: Hypernetworks for fast personalization of text-to-image models","author":"Ruiz Nataniel","year":"2024","unstructured":"Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Wei Wei, Tingbo Hou, Yael Pritch, Neal Wadhwa, Michael Rubinstein, and Kfir Aberman. 2024. Hyperdreambooth: Hypernetworks for fast personalization of text-to-image models. In CVPR. 6527-6536.","journal-title":"CVPR."},{"key":"e_1_3_2_1_45_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35 (2022), 36479-36494."},{"key":"e_1_3_2_1_46_1","unstructured":"Christoph Schuhmann. 2022. CLIPMLP Aesthetic Score Predictor. https:\/\/github.com\/christophschuhmann\/improved-aesthetic-predictor"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","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, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: an open large-scale dataset for training next generation image-text models. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 1833, 17 pages."},{"key":"e_1_3_2_1_48_1","unstructured":"Maximilian Seitzer. 2020. pytorch-fid: FID Score for PyTorch. https:\/\/github.com\/mseitzer\/pytorch-fid. Version 0.3.0."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Viraj Shah Nataniel Ruiz Forrester Cole Erika Lu Svetlana Lazebnik Yuanzhen Li and Varun Jampani. 2023. ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs. arXiv:2311.13600 [cs.CV] https:\/\/arxiv.org\/abs\/2311.13600","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"e_1_3_2_1_50_1","volume-title":"International Conference on Machine Learning. PMLR, 2256-2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning. PMLR, 2256-2265."},{"key":"e_1_3_2_1_51_1","volume-title":"Irina Blok, Huiwen Chang, Jarred Barber, Lu Jiang, Glenn Entis, Yuanzhen Li, et al.","author":"Sohn Kihyuk","year":"2023","unstructured":"Kihyuk Sohn, Nataniel Ruiz, Kimin Lee, Daniel Castro Chin, Irina Blok, Huiwen Chang, Jarred Barber, Lu Jiang, Glenn Entis, Yuanzhen Li, et al., 2023. Styledrop: Text-to-image generation in any style. arXiv preprint arXiv:2306.00983 (2023)."},{"key":"e_1_3_2_1_52_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. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_53_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2022. Denoising Diffusion Implicit Models. arXiv:2010.02502 [cs.LG] https:\/\/arxiv.org\/abs\/2010.02502"},{"key":"e_1_3_2_1_54_1","volume-title":"Towards Accurate Generative Models of Video: A New Metric & Challenges. ArXiv","author":"Unterthiner Thomas","year":"2018","unstructured":"Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach, Rapha\u00ebl Marinier, Marcin Michalski, and Sylvain Gelly. 2018. Towards Accurate Generative Models of Video: A New Metric & Challenges. ArXiv, Vol. abs\/1812.01717 (2018). https:\/\/api.semanticscholar.org\/CorpusID:54458806"},{"key":"e_1_3_2_1_55_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_56_1","volume-title":"Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers.","author":"von Platen Patrick","year":"2022","unstructured":"Patrick von Platen, Suraj Patil, Anton Lozhkov, Pedro Cuenca, Nathan Lambert, Kashif Rasul, Mishig Davaadorj, Dhruv Nair, Sayak Paul, William Berman, Yiyi Xu, Steven Liu, and Thomas Wolf. 2022. Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers."},{"key":"e_1_3_2_1_57_1","volume-title":"Taming rectified flow for inversion and editing. arXiv preprint arXiv:2411.04746","author":"Wang Jiangshan","year":"2024","unstructured":"Jiangshan Wang, Junfu Pu, Zhongang Qi, Jiayi Guo, Yue Ma, Nisha Huang, Yuxin Chen, Xiu Li, and Ying Shan. 2024a. Taming rectified flow for inversion and editing. arXiv preprint arXiv:2411.04746 (2024)."},{"key":"e_1_3_2_1_58_1","volume-title":"Styleadapter: A single-pass lora-free model for stylized image generation. arXiv preprint arXiv:2309.01770","author":"Wang Zhouxia","year":"2023","unstructured":"Zhouxia Wang, Xintao Wang, Liangbin Xie, Zhongang Qi, Ying Shan, Wenping Wang, and Ping Luo. 2023. Styleadapter: A single-pass lora-free model for stylized image generation. arXiv preprint arXiv:2309.01770 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Styleadapter: A unified stylized image generation model. International Journal of Computer Vision","author":"Wang Zhouxia","year":"2024","unstructured":"Zhouxia Wang, Xintao Wang, Liangbin Xie, Zhongang Qi, Ying Shan, Wenping Wang, and Ping Luo. 2024b. Styleadapter: A unified stylized image generation model. International Journal of Computer Vision (2024), 1-18."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35483"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02652"},{"key":"e_1_3_2_1_62_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721","author":"Ye Hu","year":"2023","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 preprint arXiv:2308.06721 (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"}],"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\/3746027.3754942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:17:19Z","timestamp":1765340239000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754942"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":65,"alternative-id":["10.1145\/3746027.3754942","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754942","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"}}]}}