{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:46:27Z","timestamp":1781797587964,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ISF","award":["3441\/21,2492\/20"],"award-info":[{"award-number":["3441\/21,2492\/20"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687612","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T08:14:37Z","timestamp":1733213677000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6973-9975","authenticated-orcid":false,"given":"Gilad","family":"Deutch","sequence":"first","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4875-965X","authenticated-orcid":false,"given":"Rinon","family":"Gal","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel and NVIDIA Research, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4261-6153","authenticated-orcid":false,"given":"Daniel","family":"Garibi","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7757-6137","authenticated-orcid":false,"given":"Or","family":"Patashnik","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6777-7445","authenticated-orcid":false,"given":"Daniel","family":"Cohen-Or","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"e_1_3_3_2_4_1","unstructured":"Yuval Alaluf Daniel Garibi Or Patashnik Hadar Averbuch-Elor and Daniel Cohen-Or. 2023a. Cross-image attention for zero-shot appearance transfer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.03335 (2023)."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Yuval Alaluf Or Patashnik and Daniel Cohen-Or. 2021a. ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.02699 (2021).","DOI":"10.1109\/ICCV48922.2021.00664"},{"key":"e_1_3_3_2_6_1","unstructured":"Yuval Alaluf Elad Richardson Gal Metzer and Daniel Cohen-Or. 2023b. A Neural Space-Time Representation for Text-to-Image Personalization. arxiv:https:\/\/arXiv.org\/abs\/2305.15391\u00a0[cs.CV]"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Yuval Alaluf Omer Tov Ron Mokady Rinon Gal and Amit\u00a0H. Bermano. 2021b. HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing. arxiv:https:\/\/arXiv.org\/abs\/2111.15666\u00a0[cs.CV]","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","unstructured":"Omri Avrahami Ohad Fried and Dani Lischinski. 2023. Blended Latent Diffusion. ACM Trans. Graph. 42 4 Article 149 (jul 2023) 11\u00a0pages. 10.1145\/3592450https:\/\/dl.acm.org\/doi\/10.1145\/3592450","DOI":"10.1145\/3592450"},{"key":"e_1_3_3_2_9_1","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:https:\/\/arXiv.org\/abs\/2311.16711 (2023)."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"e_1_3_3_2_13_1","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems 34 (2021) 8780\u20138794."},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01110"},{"key":"e_1_3_3_2_15_1","unstructured":"Ziyi Dong Pengxu Wei and Liang Lin. 2022. Dreamartist: Towards controllable one-shot text-to-image generation via positive-negative prompt-tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.11337 (2022)."},{"key":"e_1_3_3_2_16_1","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:https:\/\/arXiv.org\/abs\/2208.01618 (2022)."},{"key":"e_1_3_3_2_17_1","unstructured":"Rinon Gal Moab Arar Yuval Atzmon Amit\u00a0H Bermano Gal Chechik and Daniel Cohen-Or. 2023. Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.12228 (2023)."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Rinon Gal Or Lichter Elad Richardson Or Patashnik Amit\u00a0H. Bermano Gal Chechik and Daniel Cohen-Or. 2024. LCM-Lookahead for Encoder-based Text-to-Image Personalization. arxiv:https:\/\/arXiv.org\/abs\/2404.03620\u00a0[cs.CV]","DOI":"10.1007\/978-3-031-72630-9_19"},{"key":"e_1_3_3_2_19_1","unstructured":"Rinon Gal Or Patashnik Haggai Maron Gal Chechik and Daniel Cohen-Or. 2021. Stylegan-nada: Clip-guided domain adaptation of image generators. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.00946 (2021)."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Daniel Garibi Or Patashnik Andrey Voynov Hadar Averbuch-Elor and Daniel Cohen-Or. 2024. ReNoise: Real Image Inversion Through Iterative Noising. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.14602 (2024).","DOI":"10.1007\/978-3-031-72630-9_23"},{"key":"e_1_3_3_2_21_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_3_2_22_1","unstructured":"Zinan Guo Yanze Wu Zhuowei Chen Lang Chen and Qian He. 2024. PuLID: Pure and Lightning ID Customization via Contrastive Alignment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.16022 (2024)."},{"key":"e_1_3_3_2_23_1","unstructured":"Ligong Han Song Wen Qi Chen Zhixing Zhang Kunpeng Song Mengwei Ren Ruijiang Gao Yuxiao Chen Di Liu Qilong Zhangli et\u00a0al. 2023. Improving negative-prompt inversion via proximal guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.05414 (2023)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Amir Hertz Kfir Aberman and Daniel Cohen-Or. 2023a. Delta Denoising Score. arxiv:https:\/\/arXiv.org\/abs\/2304.07090\u00a0[cs.CV]","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"e_1_3_3_2_25_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. (2022)."},{"key":"e_1_3_3_2_26_1","unstructured":"Amir Hertz Andrey Voynov Shlomi Fruchter and Daniel Cohen-Or. 2023b. Style aligned image generation via shared attention. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.02133 (2023)."},{"key":"e_1_3_3_2_27_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_2_28_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_3_2_29_1","unstructured":"Inbar Huberman-Spiegelglas Vladimir Kulikov and Tomer Michaeli. 2023. An Edit Friendly DDPM Noise Space: Inversion and Manipulations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.06140 (2023)."},{"key":"e_1_3_3_2_30_1","unstructured":"Tero Karras Miika Aittala Timo Aila and Samuli Laine. 2022. Elucidating the design space of diffusion-based generative models. Advances in Neural Information Processing Systems 35 (2022) 26565\u201326577."},{"key":"e_1_3_3_2_31_1","unstructured":"Oren Katzir Or Patashnik Daniel Cohen-Or and Dani Lischinski. 2023. Noise-Free Score Distillation. arxiv:https:\/\/arXiv.org\/abs\/2310.17590\u00a0[cs.CV]"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_3_2_33_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Kim Dongjun","year":"2024","unstructured":"Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, and Stefano Ermon. 2024. Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ymjI8feDTD"},{"key":"e_1_3_3_2_34_1","unstructured":"Shanchuan Lin Anran Wang and Xiao Yang. 2024. SDXL-Lightning: Progressive Adversarial Diffusion Distillation. arxiv:https:\/\/arXiv.org\/abs\/2402.13929\u00a0[cs.CV]"},{"key":"e_1_3_3_2_35_1","volume-title":"International Conference on Learning Representations","author":"Liu Luping","year":"2022","unstructured":"Luping Liu, Yi Ren, Zhijie Lin, and Zhou Zhao. 2022. Pseudo Numerical Methods for Diffusion Models on Manifolds. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PlKWVd2yBkY"},{"key":"e_1_3_3_2_36_1","volume-title":"Advances in Neural Information Processing Systems","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps. In Advances in Neural Information Processing Systems, Alice\u00a0H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=2uAaGwlP_V"},{"key":"e_1_3_3_2_37_1","unstructured":"Cheng Lu Yuhao Zhou Fan Bao Jianfei Chen Chongxuan Li and Jun Zhu. 2023. DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. https:\/\/openreview.net\/forum?id=4vGwQqviud5"},{"key":"e_1_3_3_2_38_1","unstructured":"Simian Luo Yiqin Tan Longbo Huang Jian Li and Hang Zhao. 2023a. Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference. arxiv:https:\/\/arXiv.org\/abs\/2310.04378\u00a0[cs.CV]"},{"key":"e_1_3_3_2_39_1","unstructured":"Simian Luo Yiqin Tan Suraj Patil Daniel Gu Patrick von Platen Apolin\u00e1rio Passos Longbo Huang Jian Li and Hang Zhao. 2023b. LCM-LoRA: A Universal Stable-Diffusion Acceleration Module. arxiv:https:\/\/arXiv.org\/abs\/2311.05556\u00a0[cs.CV]"},{"key":"e_1_3_3_2_40_1","unstructured":"Barak Meiri Dvir Samuel Nir Darshan Gal Chechik Shai Avidan and Rami Ben-Ari. 2023. Fixed-point Inversion for Text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.12540 (2023)."},{"key":"e_1_3_3_2_41_1","volume-title":"International Conference on Learning Representations","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."},{"key":"e_1_3_3_2_42_1","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:https:\/\/arXiv.org\/abs\/2305.16807 (2023)."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_3_2_44_1","unstructured":"Alex Nichol Prafulla Dhariwal Aditya Ramesh Pranav Shyam Pamela Mishkin Bob McGrew Ilya Sutskever and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.10741 (2021)."},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01458"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01111"},{"key":"e_1_3_3_2_47_1","unstructured":"Gaurav Parmar Taesung Park Srinivasa Narasimhan and Jun-Yan Zhu. 2024. One-Step Image Translation with Text-to-Image Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.12036 (2024)."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"crossref","unstructured":"Gaurav Parmar Krishna\u00a0Kumar Singh Richard Zhang Yijun Li Jingwan Lu and Jun-Yan Zhu. 2023. Zero-shot Image-to-Image Translation. arxiv:https:\/\/arXiv.org\/abs\/2302.03027\u00a0[cs.CV]","DOI":"10.1145\/3588432.3591513"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"e_1_3_3_2_50_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell Dustin","year":"2024","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2024. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=di52zR8xgf"},{"key":"e_1_3_3_2_51_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=FjNys5c7VyY"},{"key":"e_1_3_3_2_52_1","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark et\u00a0al. 2021. Learning transferable visual models from natural language supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.00020 (2021)."},{"key":"e_1_3_3_2_53_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 (2022)."},{"key":"e_1_3_3_2_54_1","unstructured":"Elad Richardson Yuval Alaluf Or Patashnik Yotam Nitzan Yaniv Azar Stav Shapiro and Daniel Cohen-Or. 2020. Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2008.00951 (2020)."},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"crossref","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Yael Pritch Michael Rubinstein and Kfir Aberman. 2022. DreamBooth: Fine Tuning Text-to-image Diffusion Models for Subject-Driven Generation. (2022).","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_3_2_57_1","volume-title":"International Conference on Learning Representations","author":"Salimans Tim","year":"2022","unstructured":"Tim Salimans and Jonathan Ho. 2022. Progressive Distillation for Fast Sampling of Diffusion Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TIdIXIpzhoI"},{"key":"e_1_3_3_2_58_1","unstructured":"Axel Sauer Dominik Lorenz Andreas Blattmann and Robin Rombach. 2023. Adversarial Diffusion Distillation. arxiv:https:\/\/arXiv.org\/abs\/2311.17042\u00a0[cs.CV]"},{"key":"e_1_3_3_2_59_1","first-page":"2256","volume-title":"International conference on machine learning","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\u20132265."},{"key":"e_1_3_3_2_60_1","volume-title":"International Conference on Learning Representations","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619743"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"crossref","unstructured":"Yoad Tewel Omri Kaduri Rinon Gal Yoni Kasten Lior Wolf Gal Chechik and Yuval Atzmon. 2024. Training-Free Consistent Text-to-Image Generation. arxiv:https:\/\/arXiv.org\/abs\/2402.03286\u00a0[cs.CV]","DOI":"10.1145\/3658157"},{"key":"e_1_3_3_2_63_1","unstructured":"Omer Tov Yuval Alaluf Yotam Nitzan Or Patashnik and Daniel Cohen-Or. 2021. Designing an Encoder for StyleGAN Image Manipulation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2102.02766 (2021)."},{"key":"e_1_3_3_2_64_1","unstructured":"Linoy Tsaban and Apolin\u00e1rio Passos. 2023. Ledits: Real image editing with ddpm inversion and semantic guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.00522 (2023)."},{"key":"e_1_3_3_2_65_1","unstructured":"Narek Tumanyan Michal Geyer Shai Bagon and Tali Dekel. 2022a. Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.12572 (2022)."},{"key":"e_1_3_3_2_66_1","unstructured":"Narek Tumanyan Michal Geyer Shai Bagon and Tali Dekel. 2022b. Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation. arxiv:https:\/\/arXiv.org\/abs\/2211.12572\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.12572"},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"crossref","unstructured":"Dani Valevski Matan Kalman Eyal Molad Eyal Segalis Yossi Matias and Yaniv Leviathan. 2023. Unitune: Text-driven image editing by fine tuning a diffusion model on a single image. ACM Transactions on Graphics (TOG) 42 4 (2023) 1\u201310.","DOI":"10.1145\/3592451"},{"key":"e_1_3_3_2_68_1","unstructured":"Andrey Voynov Qinghao Chu Daniel Cohen-Or and Kfir Aberman. 2023. p+: Extended textual conditioning in text-to-image generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.09522 (2023)."},{"key":"e_1_3_3_2_69_1","unstructured":"Jiacheng Wang Ping Liu and Wei Xu. 2024. Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance. arxiv:https:\/\/arXiv.org\/abs\/2401.02126\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2401.02126"},{"key":"e_1_3_3_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"e_1_3_3_2_71_1","unstructured":"Jie Xiao Kai Zhu Han Zhang Zhiheng Liu Yujun Shen Yu Liu Xueyang Fu and Zheng-Jun Zha. 2023. CCM: Adding Conditional Controls to Text-to-Image Consistency Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.06971 (2023)."},{"key":"e_1_3_3_2_72_1","unstructured":"Tianwei Yin Micha\u00ebl Gharbi Richard Zhang Eli Shechtman Fr\u00e9do Durand William\u00a0T Freeman and Taesung Park. 2024. One-step Diffusion with Distribution Matching Distillation. CVPR (2024)."},{"key":"e_1_3_3_2_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_74_1","doi-asserted-by":"crossref","unstructured":"Yuxin Zhang Weiming Dong Fan Tang Nisha Huang Haibin Huang Chongyang Ma Tong-Yee Lee Oliver Deussen and Changsheng Xu. 2023. ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models. ACM Transactions on Graphics (TOG) 42 6 (2023) 244:1\u2013244:14.","DOI":"10.1145\/3618342"},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"e_1_3_3_2_76_1","unstructured":"Peihao Zhu Rameen Abdal Yipeng Qin and Peter Wonka. 2020. Improved StyleGAN Embedding: Where are the Good Latents? arxiv:https:\/\/arXiv.org\/abs\/2012.09036\u00a0[cs.CV]"}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Conference Papers","location":"Tokyo Japan","acronym":"SA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2024 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687612","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:26Z","timestamp":1750294706000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687612"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":75,"alternative-id":["10.1145\/3680528.3687612","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687612","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}