{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:08:18Z","timestamp":1784268498058,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"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\/3641519.3657407","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:39:28Z","timestamp":1720780768000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":49,"title":["I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9140-4724","authenticated-orcid":false,"given":"Xun","family":"Guo","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3705-4592","authenticated-orcid":false,"given":"Mingwu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4904-5694","authenticated-orcid":false,"given":"Liang","family":"Hou","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1198-9954","authenticated-orcid":false,"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2335-3191","authenticated-orcid":false,"given":"Yufan","family":"Deng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-565X","authenticated-orcid":false,"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5475-2728","authenticated-orcid":false,"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8426-9335","authenticated-orcid":false,"given":"Yufan","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9237-8825","authenticated-orcid":false,"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zhengjun","family":"Zha","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7787-6428","authenticated-orcid":false,"given":"Haibin","family":"Huang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8243-9513","authenticated-orcid":false,"given":"Chongyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_2_2_1","volume-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127","author":"Blattmann Andreas","year":"2023","unstructured":"Andreas Blattmann, Tim Dockhorn, Sumith Kulal, Daniel Mendelevitch, Maciej Kilian, Dominik Lorenz, Yam Levi, Zion English, Vikram Voleti, Adam Letts, 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_2_4_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang Chao Weng and Ying Shan. 2023c. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation. arxiv:2310.19512\u00a0[cs.CV]"},{"key":"e_1_3_2_2_5_1","volume-title":"LivePhoto: Real Image Animation with Text-guided Motion Control. arXiv preprint arXiv:2312.02928","author":"Chen Xi","year":"2023","unstructured":"Xi Chen, Zhiheng Liu, Mengting Chen, Yutong Feng, Yu Liu, Yujun Shen, and Hengshuang Zhao. 2023a. LivePhoto: Real Image Animation with Text-guided Motion Control. arXiv preprint arXiv:2312.02928 (2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"Seine: Short-to-long video diffusion model for generative transition and prediction. arXiv preprint arXiv:2310.20700","author":"Chen Xinyuan","year":"2023","unstructured":"Xinyuan Chen, Yaohui Wang, Lingjun Zhang, Shaobin Zhuang, Xin Ma, Jiashuo Yu, Yali Wang, Dahua Lin, Yu Qiao, and Ziwei Liu. 2023b. Seine: Short-to-long video diffusion model for generative transition and prediction. arXiv preprint arXiv:2310.20700 (2023)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_8_1","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. In Advances in neural information processing systems. 8780\u20138794."},{"key":"e_1_3_2_2_9_1","volume-title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning. arXiv preprint arXiv:2311.10709","author":"Girdhar Rohit","year":"2023","unstructured":"Rohit Girdhar, Mannat Singh, Andrew Brown, Quentin Duval, Samaneh Azadi, Sai\u00a0Saketh Rambhatla, Akbar Shah, Xi Yin, Devi Parikh, and Ishan Misra. 2023. Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning. arXiv preprint arXiv:2311.10709 (2023)."},{"key":"e_1_3_2_2_10_1","volume-title":"Sparsectrl: Adding sparse controls to text-to-video diffusion models. arXiv preprint arXiv:2311.16933","author":"Guo Yuwei","year":"2023","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2023. Sparsectrl: Adding sparse controls to text-to-video diffusion models. arXiv preprint arXiv:2311.16933 (2023)."},{"key":"e_1_3_2_2_11_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_13_1","volume-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths. arXiv preprint arXiv:2211.13221","author":"He Yingqing","year":"2022","unstructured":"Yingqing He, Tianyu Yang, Yong Zhang, Ying Shan, and Qifeng Chen. 2022. Latent video diffusion models for high-fidelity video generation with arbitrary lengths. arXiv preprint arXiv:2211.13221 (2022)."},{"key":"e_1_3_2_2_14_1","volume-title":"Prompt-to-Prompt Image Editing with Cross-Attention Control. In International Conference on Learning Representations (ICLR).","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. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_15_1","volume":"202","author":"Ho Jonathan","unstructured":"Jonathan Ho, William Chan, Chitwan Saharia, Jay Whang, Ruiqi Gao, Alexey Gritsenko, Diederik\u00a0P Kingma, Ben Poole, Mohammad Norouzi, David\u00a0J Fleet, 2022. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022).","journal-title":"J Fleet"},{"key":"e_1_3_2_2_16_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Advances in neural information processing systems. 6840\u20136851."},{"key":"e_1_3_2_2_17_1","volume-title":"International Conference on Machine Learning. PMLR, 2790\u20132799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De\u00a0Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790\u20132799."},{"key":"e_1_3_2_2_18_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations (ICLR). OpenReview.net.","author":"Hu J.","year":"2022","unstructured":"Edward\u00a0J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations (ICLR). OpenReview.net."},{"key":"e_1_3_2_2_19_1","volume-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117","author":"Hu Li","year":"2023","unstructured":"Li Hu, Xin Gao, Peng Zhang, Ke Sun, Bang Zhang, and Liefeng Bo. 2023. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117 (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma P","year":"2013","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_2_21_1","volume-title":"Videogen: A reference-guided latent diffusion approach for high definition text-to-video generation. arXiv preprint arXiv:2309.00398","author":"Li Xin","year":"2023","unstructured":"Xin Li, Wenqing Chu, Ye Wu, Weihang Yuan, Fanglong Liu, Qi Zhang, Fu Li, Haocheng Feng, Errui Ding, and Jingdong Wang. 2023. Videogen: A reference-guided latent diffusion approach for high definition text-to-video generation. arXiv preprint arXiv:2309.00398 (2023)."},{"key":"e_1_3_2_2_22_1","volume-title":"Evalcrafter: Benchmarking and evaluating large video generation models. arXiv preprint arXiv:2310.11440","author":"Liu Yaofang","year":"2023","unstructured":"Yaofang Liu, Xiaodong Cun, Xuebo Liu, Xintao Wang, Yong Zhang, Haoxin Chen, Yang Liu, Tieyong Zeng, Raymond Chan, and Ying Shan. 2023. Evalcrafter: Benchmarking and evaluating large video generation models. arXiv preprint arXiv:2310.11440 (2023)."},{"key":"e_1_3_2_2_23_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_24_1","volume-title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In International Conference on Learning Representations (ICLR).","author":"Meng Chenlin","year":"2022","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_25_1","volume-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453","author":"Mou Chong","year":"2023","unstructured":"Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, and Xiaohu Qie. 2023. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)."},{"key":"e_1_3_2_2_26_1","unstructured":"John Mullan Duncan Crawbuck and Aakash Sastry. 2023. Hotshot-XL. https:\/\/github.com\/hotshotco\/hotshot-xl."},{"key":"e_1_3_2_2_27_1","volume-title":"Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193","author":"Oquab Maxime","year":"2023","unstructured":"Maxime Oquab, Timoth\u00e9e Darcet, Th\u00e9o Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_2_28_1","unstructured":"Pika. 2023. Pika. https:\/\/pika.art\/."},{"key":"e_1_3_2_2_29_1","unstructured":"PlaygroundAI. 2023. MJHQ-30K Dataset. https:\/\/huggingface.co\/datasets\/playgroundai\/MJHQ-30K."},{"key":"e_1_3_2_2_30_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. CoRR 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. CoRR abs\/2307.01952 (2023)."},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event(Proceedings of Machine Learning Research, Vol.\u00a0139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748\u20138763."},{"key":"e_1_3_2_2_33_1","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (CVPR). IEEE, 10674\u201310685","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (CVPR). IEEE, 10674\u201310685."},{"key":"e_1_3_2_2_34_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference","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\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234\u2013241."},{"key":"e_1_3_2_2_35_1","volume-title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. IEEE, 22500\u201322510."},{"key":"e_1_3_2_2_36_1","unstructured":"RunwayAI. 2023. Gen-2: The Next Step Forward for Generative AI. https:\/\/research.runwayml.com\/gen2."},{"key":"e_1_3_2_2_37_1","volume-title":"Denoising Diffusion Implicit Models. In International Conference on Learning Representations (ICLR).","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020a. Denoising Diffusion Implicit Models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_38_1","volume-title":"International Conference on Learning Representations (ICLR).","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. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_39_1","volume-title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow. In ECCV (2)(Lecture Notes in Computer Science, Vol.\u00a012347)","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. RAFT: Recurrent All-Pairs Field Transforms for Optical Flow. In ECCV (2)(Lecture Notes in Computer Science, Vol.\u00a012347). Springer, 402\u2013419."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_2_41_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems."},{"key":"e_1_3_2_2_42_1","unstructured":"Vikram Voleti Alexia Jolicoeur-Martineau and Chris Pal. 2022. MCVD-masked conditional video diffusion for prediction generation and interpolation. In Advances in Neural Information Processing Systems. 23371\u201323385."},{"key":"e_1_3_2_2_43_1","volume-title":"Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571","author":"Wang Jiuniu","year":"2023","unstructured":"Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, and Shiwei Zhang. 2023b. Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)."},{"key":"e_1_3_2_2_44_1","unstructured":"Xiang Wang Hangjie Yuan Shiwei Zhang Dayou Chen Jiuniu Wang Yingya Zhang Yujun Shen Deli Zhao and Jingren Zhou. 2023c. VideoComposer: Compositional Video Synthesis with Motion Controllability. In Advances in Neural Information Processing Systems. 7594\u20137611."},{"key":"e_1_3_2_2_45_1","volume-title":"Lavie: High-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103","author":"Wang Yaohui","year":"2023","unstructured":"Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, 2023a. Lavie: High-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103 (2023)."},{"key":"e_1_3_2_2_46_1","volume-title":"Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462","author":"Witteveen Sam","year":"2022","unstructured":"Sam Witteveen and Martin Andrews. 2022. Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462 (2022)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"e_1_3_2_2_48_1","volume-title":"Lamp: Learn a motion pattern for few-shot-based video generation. arXiv preprint arXiv:2310.10769","author":"Wu Ruiqi","year":"2023","unstructured":"Ruiqi Wu, Liangyu Chen, Tong Yang, Chunle Guo, Chongyi Li, and Xiangyu Zhang. 2023a. Lamp: Learn a motion pattern for few-shot-based video generation. arXiv preprint arXiv:2310.10769 (2023)."},{"key":"e_1_3_2_2_49_1","volume-title":"Dynamicrafter: Animating open-domain images with video diffusion priors. arXiv preprint arXiv:2310.12190","author":"Xing Jinbo","year":"2023","unstructured":"Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Xintao Wang, Tien-Tsin Wong, and Ying Shan. 2023. Dynamicrafter: Animating open-domain images with video diffusion priors. arXiv preprint arXiv:2310.12190 (2023)."},{"key":"e_1_3_2_2_50_1","volume-title":"Magicanimate: Temporally consistent human image animation using diffusion model. arXiv preprint arXiv:2311.16498","author":"Xu Zhongcong","year":"2023","unstructured":"Zhongcong Xu, Jianfeng Zhang, Jun\u00a0Hao Liew, Hanshu Yan, Jia-Wei Liu, Chenxu Zhang, Jiashi Feng, and Mike\u00a0Zheng Shou. 2023. Magicanimate: Temporally consistent human image animation using diffusion model. arXiv preprint arXiv:2311.16498 (2023)."},{"key":"e_1_3_2_2_51_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_2_52_1","volume-title":"Make Pixels Dance: High-Dynamic Video Generation. arXiv preprint arXiv:2311.10982","author":"Zeng Yan","year":"2023","unstructured":"Yan Zeng, Guoqiang Wei, Jiani Zheng, Jiaxin Zou, Yang Wei, Yuchen Zhang, and Hang Li. 2023. Make Pixels Dance: High-Dynamic Video Generation. arXiv preprint arXiv:2311.10982 (2023)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_54_1","volume-title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models. arXiv preprint arXiv:2311.04145","author":"Zhang Shiwei","year":"2023","unstructured":"Shiwei Zhang, Jiayu Wang, Yingya Zhang, Kang Zhao, Hangjie Yuan, Zhiwu Qing, Xiang Wang, Deli Zhao, and Jingren Zhou. 2023b. I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models. arXiv preprint arXiv:2311.04145 (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"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657407","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:35Z","timestamp":1750295375000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":53,"alternative-id":["10.1145\/3641519.3657407","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657407","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"}}]}}