{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:06:35Z","timestamp":1761897995642,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nd\/4.0\/"}],"funder":[{"name":"Shenzhen Science and Technology Innovation Commission","award":["JCYJ20200109114835623,JSGG20220831105002004"],"award-info":[{"award-number":["JCYJ20200109114835623,JSGG20220831105002004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658020","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"878-887","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["SBCR: Stochasticity Beats Content Restriction Problem in Training and Tuning Free Image Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2826-9231","authenticated-orcid":false,"given":"Jiancheng","family":"Huang","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4820-0704","authenticated-orcid":false,"given":"Mingfu","family":"Yan","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0187-8544","authenticated-orcid":false,"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0677-7358","authenticated-orcid":false,"given":"Shifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Blended latent diffusion. arXiv preprint arXiv:2206.02779","author":"Avrahami Omri","year":"2022","unstructured":"Omri Avrahami, Ohad Fried, and Dani Lischinski. 2022a. Blended latent diffusion. arXiv preprint arXiv:2206.02779 (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"Blended Latent Diffusion. arXiv preprint arXiv:2206.02779","author":"Avrahami Omri","year":"2022","unstructured":"Omri Avrahami, Ohad Fried, and Dani Lischinski. 2022b. Blended Latent Diffusion. arXiv preprint arXiv:2206.02779 (2022)."},{"key":"e_1_3_2_1_3_1","volume-title":"LEDITS: Limitless Image Editing using Text-to-Image Models. arXiv preprint arXiv:2311.16711","author":"Brack Manuel","year":"2023","unstructured":"Manuel Brack, Felix Friedrich, Katharina Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, and Apolin\u00e1rio Passos. 2023. LEDITS: Limitless Image Editing using Text-to-Image Models. arXiv preprint arXiv:2311.16711 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Tim Brooks Aleksander Holynski and Alexei A Efros. 2023. Instructpix2pix: Learning to follow image editing instructions. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_5_1","unstructured":"Mingdeng Cao Xintao Wang Zhongang Qi Ying Shan Xiaohu Qie and Yinqiang Zheng. 2023. MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing. In ICCV."},{"key":"e_1_3_2_1_6_1","volume-title":"2023 a. FEC: Three Finetuning-free Methods to Enhance Consistency for Real Image Editing. arXiv preprint arXiv:2309.14934","author":"Chen Songyan","year":"2023","unstructured":"Songyan Chen and Jiancheng Huang. 2023 a. FEC: Three Finetuning-free Methods to Enhance Consistency for Real Image Editing. arXiv preprint arXiv:2309.14934 (2023)."},{"volume-title":"2023 b. SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing. In 2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)","author":"Chen Songyan","key":"e_1_3_2_1_7_1","unstructured":"Songyan Chen and Jiancheng Huang. 2023 b. SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing. In 2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML). IEEE, 369--375."},{"key":"e_1_3_2_1_8_1","volume-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427","author":"Couairon Guillaume","year":"2022","unstructured":"Guillaume Couairon, Jakob Verbeek, Holger Schwenk, and Matthieu Cord. 2022. DiffEdit: Diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)."},{"key":"e_1_3_2_1_9_1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. NeurIPS , Vol. 34 (2021), 8780--8794.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_10_1","volume-title":"Yinfei Yang, and Zhe Gan.","author":"Fu Tsu-Jui","year":"2023","unstructured":"Tsu-Jui Fu, Wenze Hu, Xianzhi Du, William Yang Wang, Yinfei Yang, and Zhe Gan. 2023. Guiding instruction-based image editing via multimodal large language models. arXiv preprint arXiv:2309.17102 (2023)."},{"key":"e_1_3_2_1_11_1","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. In ICLR."},{"key":"e_1_3_2_1_12_1","unstructured":"Shuyang Gu Dong Chen Jianmin Bao Fang Wen Bo Zhang Dongdong Chen Lu Yuan and Baining Guo. 2022. Vector quantized diffusion model for text-to-image synthesis. In CVPR."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"L. Han et al. 2024. ProxEdit: Improving Tuning-Free Real Image Editing With Proximal Guidance. In WACV.","DOI":"10.1109\/WACV57701.2024.00424"},{"key":"e_1_3_2_1_14_1","unstructured":"Ligong Han Song Wen Qi Chen Zhixing Zhang Kunpeng Song Mengwei Ren Ruijiang Gao Yuxiao Chen Di Liu Qilong Zhangli et al. 2023. Improving Negative-Prompt Inversion via Proximal Guidance. arXiv preprint arXiv:2306.05414 (2023)."},{"key":"e_1_3_2_1_15_1","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 ICLR."},{"key":"e_1_3_2_1_16_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In NeurIPS."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3586589.3586636"},{"key":"e_1_3_2_1_18_1","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications.","author":"Ho Jonathan","year":"2021","unstructured":"Jonathan Ho and Tim Salimans. 2021. Classifier-free diffusion guidance. In NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications."},{"key":"e_1_3_2_1_19_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_20_1","volume-title":"2023 b. Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement. arXiv preprint arXiv:2309.14709","author":"Huang Jiancheng","year":"2023","unstructured":"Jiancheng Huang, Yifan Liu, and Shifeng Chen. 2023 b. Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement. arXiv preprint arXiv:2309.14709 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"2023 c. Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisation. arXiv preprint arXiv:2310.00546","author":"Huang Jiancheng","year":"2023","unstructured":"Jiancheng Huang, Yifan Liu, Yi Huang, and Shifeng Chen. 2023 c. Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisation. arXiv preprint arXiv:2310.00546 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Jiancheng Huang Yifan Liu Jin Qin and Shifeng Chen. 2023 d. KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editing. arxiv: 2309.16608 [cs.CV]","DOI":"10.1007\/978-981-99-8429-9_14"},{"key":"e_1_3_2_1_23_1","volume-title":"2023 a. WaveDM: Wavelet-Based Diffusion Models for Image Restoration. arXiv preprint arXiv:2305.13819","author":"Huang Yi","year":"2023","unstructured":"Yi Huang, Jiancheng Huang, Jianzhuang Liu, Yu Dong, Jiaxi Lv, and Shifeng Chen. 2023 a. WaveDM: Wavelet-Based Diffusion Models for Image Restoration. arXiv preprint arXiv:2305.13819 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"An Edit Friendly DDPM Noise Space: Inversion and Manipulations. arXiv preprint arXiv:2304.06140","author":"Huberman-Spiegelglas Inbar","year":"2023","unstructured":"Inbar Huberman-Spiegelglas, Vladimir Kulikov, and Tomer Michaeli. 2023. An Edit Friendly DDPM Noise Space: Inversion and Manipulations. arXiv preprint arXiv:2304.06140 (2023)."},{"key":"e_1_3_2_1_25_1","unstructured":"Betker James Goh Gabriel Jing Li Brooks Tim Wang Jianfeng Li Linjie Ouyang Long and et.al. 2023. Improving Image Generation with Better Captions. (2023). https:\/\/cdn.openai.com\/papers"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Jaeseok Jeong Mingi Kwon and Youngjung Uh. 2024. Training-Free Content Injection Using H-Space in Diffusion Models. In WACV. 5151--5161.","DOI":"10.1109\/WACV57701.2024.00507"},{"key":"e_1_3_2_1_27_1","volume-title":"Imagic: Text-based real image editing with diffusion models. In CVPR.","author":"Kawar Bahjat","year":"2023","unstructured":"Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, and Michal Irani. 2023. Imagic: Text-based real image editing with diffusion models. In CVPR."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Nupur Kumari Bingliang Zhang Richard Zhang Eli Shechtman and Jun-Yan Zhu. 2023. Multi-Concept Customization of Text-to-Image Diffusion. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_1_29_1","volume-title":"Conditional Score Guidance for Text-Driven Image-to-Image Translation. NIPS","author":"Lee Hyunsoo","year":"2023","unstructured":"Hyunsoo Lee, Minsoo Kang, and Bohyung Han. 2023. Conditional Score Guidance for Text-Driven Image-to-Image Translation. NIPS (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Clip-event: Connecting text and images with event structures. In CVPR.","author":"Li Manling","year":"2022","unstructured":"Manling Li, Ruochen Xu, Shuohang Wang, Luowei Zhou, Xudong Lin, Chenguang Zhu, Michael Zeng, Heng Ji, and Shih-Fu Chang. 2022. Clip-event: Connecting text and images with event structures. In CVPR."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"e_1_3_2_1_32_1","unstructured":"B. Meiri et al. 2023. Fixed-point Inversion for Text-to-image diffusion models. arXiv (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Sdedit: Image synthesis and editing with stochastic differential equations. In ICLR.","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021. Sdedit: Image synthesis and editing with stochastic differential equations. In ICLR."},{"key":"e_1_3_2_1_34_1","volume-title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models. arXiv preprint arXiv:2305.16807","author":"Miyake Daiki","year":"2023","unstructured":"Daiki Miyake, Akihiro Iohara, Yu Saito, and Toshiyuki Tanaka. 2023. Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models. arXiv preprint arXiv:2305.16807 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Ron Mokady Amir Hertz Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2023. Null-text Inversion for Editing Real Images using Guided Diffusion Models. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_36_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. In ICML.","author":"Nichol Alex","year":"2022","unstructured":"Alex 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 ICML."},{"key":"e_1_3_2_1_37_1","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In ICML. PMLR 8162--8171."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Z. Pan et al. 2023. Effective real image editing with accelerated iterative diffusion inversion. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01458"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Dong Huk Park Grace Luo Clayton Toste Samaneh Azadi Xihui Liu Maka Karalashvili Anna Rohrbach and Trevor Darrell. 2024. Shape-Guided Diffusion With Inside-Outside Attention. In WACV. 4198--4207.","DOI":"10.1109\/WACV57701.2024.00415"},{"key":"e_1_3_2_1_40_1","volume-title":"Sang Wan Lee, and Jong Chul Ye","author":"Park Geon Yeong","year":"2023","unstructured":"Geon Yeong Park, Jeongsol Kim, Beomsu Kim, Sang Wan Lee, and Jong Chul Ye. 2023. Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models. NIPS (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Richard Zhang, Yijun Li, Jingwan Lu, and Jun-Yan Zhu.","author":"Parmar Gaurav","year":"2023","unstructured":"Gaurav Parmar, Krishna Kumar Singh, Richard Zhang, Yijun Li, Jingwan Lu, and Jun-Yan Zhu. 2023. Zero-shot Image-to-Image Translation. In ACM SIGGRAPH."},{"key":"e_1_3_2_1_42_1","volume-title":"Localizing Object-level Shape Variations with Text-to-Image Diffusion Models. ICCV","author":"Patashnik Or","year":"2023","unstructured":"Or Patashnik, Daniel Garibi, Idan Azuri, Hadar Averbuch-Elor, and Daniel Cohen-Or. 2023. Localizing Object-level Shape Variations with Text-to-Image Diffusion Models. ICCV (2023)."},{"key":"e_1_3_2_1_43_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_1_44_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_45_1","volume-title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In CVPR.","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."},{"key":"e_1_3_2_1_46_1","volume-title":"Burcu Karagol Ayan, S Sara Mahdavi, Rapha Gontijo Lopes, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S Sara Mahdavi, Rapha Gontijo Lopes, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. In NeurIPS."},{"key":"e_1_3_2_1_47_1","unstructured":"Jascha Sohl-Dickstein Eric Weiss Niru Maheswaranathan and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In ICML."},{"key":"e_1_3_2_1_48_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2020a. Denoising diffusion implicit models. In ICLR."},{"key":"e_1_3_2_1_49_1","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. In NeurIPS."},{"key":"e_1_3_2_1_50_1","volume-title":"Improved techniques for training score-based generative models. NeurIPS","author":"Song Yang","year":"2020","unstructured":"Yang Song and Stefano Ermon. 2020. Improved techniques for training score-based generative models. NeurIPS (2020)."},{"key":"e_1_3_2_1_51_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 P 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_1_52_1","volume-title":"LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance. arxiv: 2307.00522 [cs.CV]","author":"Tsaban Linoy","year":"2023","unstructured":"Linoy Tsaban and Apolin\u00e1rio Passos. 2023. LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance. arxiv: 2307.00522 [cs.CV]"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Narek Tumanyan Michal Geyer Shai Bagon and Tali Dekel. 2023. Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_1_54_1","volume-title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation. In ICCV.","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. In ICCV."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"e_1_3_2_1_56_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 T 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_1_57_1","volume-title":"Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al.","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al. 2022. Scaling autoregressive models for content-rich text-to-image generation. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_2_1_58_1","volume-title":"FISEdit: Accelerating Text-to-image Editing via Cache-enabled Sparse Diffusion Inference. AAAI","author":"Yu Zihao","year":"2024","unstructured":"Zihao Yu, Haoyang Li, Fangcheng Fu, Xupeng Miao, and Bin Cui. 2024. FISEdit: Accelerating Text-to-image Editing via Cache-enabled Sparse Diffusion Inference. AAAI (2024)."},{"key":"e_1_3_2_1_59_1","volume-title":"Adding Conditional Control to Text-to-Image Diffusion Models. ICCV","author":"Zhang Lvmin","year":"2023","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. ICCV (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"Null-text Guidance in Diffusion Models is Secretly a Cartoon-style Creator. arXiv preprint arXiv:2305.06710","author":"Zhao Jing","year":"2023","unstructured":"Jing Zhao, Heliang Zheng, Chaoyue Wang, Long Lan, Wanrong Huang, and Wenjing Yang. 2023. Null-text Guidance in Diffusion Models is Secretly a Cartoon-style Creator. arXiv preprint arXiv:2305.06710 (2023)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Phuket Thailand","acronym":"ICMR '24"},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658020","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:49:37Z","timestamp":1755766177000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658020"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":60,"alternative-id":["10.1145\/3652583.3658020","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658020","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}