{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:58:06Z","timestamp":1774022286113,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["2366\/16"],"award-info":[{"award-number":["2366\/16"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730615","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:42:43Z","timestamp":1753260163000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["pOps: Photo-Inspired Diffusion Operators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1784-3736","authenticated-orcid":false,"given":"Elad","family":"Richardson","sequence":"first","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0076-1454","authenticated-orcid":false,"given":"Yuval","family":"Alaluf","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4693-3565","authenticated-orcid":false,"given":"Ali","family":"Mahdavi-Amiri","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00671"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"e_1_3_3_2_4_1","unstructured":"Yogesh Balaji Seungjun Nah Xun Huang Arash Vahdat Jiaming Song Qinsheng Zhang Karsten Kreis Miika Aittala Timo Aila Samuli Laine Bryan Catanzaro Tero Karras and Ming-Yu Liu. 2023. eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers. arxiv:https:\/\/arXiv.org\/abs\/2211.01324\u00a0[cs.CV]"},{"key":"e_1_3_3_2_5_1","unstructured":"Omer Bar-Tal Lior Yariv Yaron Lipman and Tali Dekel. 2023. Multidiffusion: Fusing diffusion paths for controlled image generation. (2023)."},{"key":"e_1_3_3_2_6_1","unstructured":"Black-Forest. 2024. Flux: Diffusion models for layered image generation. https:\/\/github.com\/black-forest-labs\/flux Accessed: 2024."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Nathalie Bonnardel and Evelyne Marm\u00e8che. 2005. Towards supporting evocation processes in creative design: A cognitive approach. International journal of human-computer studies 63 4-5 (2005) 422\u2013435.","DOI":"10.1016\/j.ijhcs.2005.04.006"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Manuel Brack Felix Friedrich Dominik Hintersdorf Lukas Struppek Patrick Schramowski and Kristian Kersting. 2024. SEGA: Instructing text-to-image models using semantic guidance. Advances in Neural Information Processing Systems 36 (2024).","DOI":"10.52202\/075280-1102"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_2_10_1","unstructured":"David\u00a0C Brown. 2008. Guiding computational design creativity research. Studying Design Creativity Springer (2008)."},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Ta-Ying Cheng Prafull Sharma Andrew Markham Niki Trigoni and Varun Jampani. 2024. ZeST: Zero-Shot Material Transfer from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.06425 (2024).","DOI":"10.1007\/978-3-031-73232-4_21"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Omer Dahary Or Patashnik Kfir Aberman and Daniel Cohen-Or. 2024. Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.16990 (2024).","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Ming Ding Wendi Zheng Wenyi Hong and Jie Tang. 2022. Cogview2: Faster and better text-to-image generation via hierarchical transformers. Advances in Neural Information Processing Systems 35 (2022) 16890\u201316902.","DOI":"10.52202\/068431-1229"},{"key":"e_1_3_3_2_14_1","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Patrick Esser Johnathan Chiu Parmida Atighehchian Jonathan Granskog and Anastasis Germanidis. 2023. Structure and content-guided video synthesis with diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.03011 (2023).","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_3_2_16_1","unstructured":"James\u00a0D Foley. 1996. 12.7 Constructive solid geometry. 533\u2013558\u00a0pages."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Stephanie Fu Netanel Tamir Shobhita Sundaram Lucy Chai Richard Zhang Tali Dekel and Phillip Isola. 2023. DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data. arxiv:https:\/\/arXiv.org\/abs\/2306.09344\u00a0[cs.CV]","DOI":"10.52202\/075280-2208"},{"key":"e_1_3_3_2_18_1","unstructured":"Rohit Gandikota Joanna Materzynska Tingrui Zhou Antonio Torralba and David Bau. 2023. Concept sliders: Lora adaptors for precise control in diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.12092 (2023)."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Milene Gon\u00e7alves Carlos Cardoso and Petra Badke-Schaub. 2014. What inspires designers? Preferences on inspirational approaches during idea generation. Design studies 35 1 (2014) 29\u201353.","DOI":"10.1016\/j.destud.2013.09.001"},{"key":"e_1_3_3_2_20_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_21_1","unstructured":"Erik H\u00e4rk\u00f6nen Aaron Hertzmann Jaakko Lehtinen and Sylvain Paris. 2020. GANSpace: Discovering Interpretable GAN Controls. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2004.02546 (2020)."},{"key":"e_1_3_3_2_22_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_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687658"},{"key":"e_1_3_3_2_24_1","unstructured":"Jaeseok Jeong Junho Kim Yunjey Choi Gayoung Lee and Youngjung Uh. 2024. Visual Style Prompting with Swapping Self-Attention. arxiv:https:\/\/arXiv.org\/abs\/2402.12974\u00a0[cs.CV]"},{"key":"e_1_3_3_2_25_1","volume-title":"Forty-first International Conference on Machine Learning","author":"Jin Chen","year":"2024","unstructured":"Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, and Philip\u00a0Alexander Teare. 2024. An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_3_2_28_1","unstructured":"Diederik\u00a0P Kingma. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.6114 (2013)."},{"key":"e_1_3_3_2_29_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lee Sharon","year":"2024","unstructured":"Sharon Lee, Yunzhi Zhang, Shangzhe Wu, and Jiajun Wu. 2024. Language-Informed Visual Concept Learning. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=juuyW8B8ig"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"e_1_3_3_2_31_1","volume-title":"International Conference on Learning Representations","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_3_2_32_1","unstructured":"Matthias Minderer Alexey Gritsenko and Neil Houlsby. 2024. Scaling open-vocabulary object detection. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","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:https:\/\/arXiv.org\/abs\/2302.08453\u00a0[cs.CV]","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_3_2_35_1","unstructured":"Kam\u00a0Woh Ng Xiatian Zhu Yi-Zhe Song and Tao Xiang. 2023. DreamCreature: Crafting Photorealistic Virtual Creatures from Imagination. arxiv:https:\/\/arXiv.org\/abs\/2311.15477\u00a0[cs.CV]"},{"key":"e_1_3_3_2_36_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_37_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et\u00a0al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.07193 (2023)."},{"key":"e_1_3_3_2_38_1","unstructured":"Ryan Po Wang Yifan Vladislav Golyanik Kfir Aberman Jonathan\u00a0T. Barron Amit\u00a0H. Bermano Eric\u00a0Ryan Chan Tali Dekel Aleksander Holynski Angjoo Kanazawa C.\u00a0Karen Liu Lingjie Liu Ben Mildenhall Matthias Nie\u00dfner Bj\u00f6rn Ommer Christian Theobalt Peter Wonka and Gordon Wetzstein. 2023. State of the Art on Diffusion Models for Visual Computing. arxiv:https:\/\/arXiv.org\/abs\/2310.07204\u00a0[cs.AI]"},{"key":"e_1_3_3_2_39_1","unstructured":"Dustin Podell Zion English Kyle Lacey Andreas Blattmann Tim Dockhorn Jonas M\u00fcller Joe Penna and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.01952 (2023)."},{"key":"e_1_3_3_2_40_1","first-page":"8748","volume-title":"International Conference on Machine Learning","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, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_2_41_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_42_1","unstructured":"Elad Richardson Kfir Goldberg Yuval Alaluf and Daniel Cohen-Or. 2023. Conceptlab: Creative generation using diffusion prior constraints. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.02669 (2023)."},{"key":"e_1_3_3_2_43_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. 10684\u201310695\u00a0pages.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00661"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"crossref","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily\u00a0L Denton Kamyar Ghasemipour Raphael Gontijo\u00a0Lopes Burcu Karagol\u00a0Ayan Tim Salimans et\u00a0al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems 35 (2022) 36479\u201336494.","DOI":"10.52202\/068431-2643"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"crossref","unstructured":"Axel Sauer Frederic Boesel Tim Dockhorn Andreas Blattmann Patrick Esser and Robin Rombach. 2024. Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.12015 (2024).","DOI":"10.1145\/3680528.3687625"},{"key":"e_1_3_3_2_47_1","unstructured":"Arseniy Shakhmatov Anton Razzhigaev Aleksandr Nikolich Vladimir Arkhipkin Igor Pavlov Andrey Kuznetsov and Denis Dimitrov. 2022. Kandinsky 2. https:\/\/github.com\/ai-forever\/Kandinsky-2."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"e_1_3_3_2_50_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Singer Uriel","year":"2023","unstructured":"Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta, and Yaniv Taigman. 2023. Make-A-Video: Text-to-Video Generation without Text-Video Data. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nJfylDvgzlq"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"crossref","unstructured":"Gemma\u00a0Canet Tarr\u00e9s Zhe Lin Zhifei Zhang Jianming Zhang Yizhi Song Dan Ruta Andrew Gilbert John Collomosse and Soo\u00a0Ye Kim. 2024. Thinking outside the bbox: Unconstrained generative object compositing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.04559 (2024).","DOI":"10.1007\/978-3-031-73033-7_27"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"crossref","unstructured":"Yael Vinker Andrey Voynov Daniel Cohen-Or and Ariel Shamir. 2023. Concept decomposition for visual exploration and inspiration. ACM Transactions on Graphics (TOG) 42 6 (2023) 1\u201313.","DOI":"10.1145\/3618315"},{"key":"e_1_3_3_2_54_1","unstructured":"Zihao Wang Lin Gui Jeffrey Negrea and Victor Veitch. 2024. Concept Algebra for (Score-Based) Text-Controlled Generative Models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Merryl\u00a0J Wilkenfeld and Thomas\u00a0B Ward. 2001. Similarity and emergence in conceptual combination. Journal of Memory and Language 45 1 (2001) 21\u201338.","DOI":"10.1006\/jmla.2000.2772"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00829"},{"key":"e_1_3_3_2_58_1","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. (2023)."},{"key":"e_1_3_3_2_59_1","unstructured":"Shukang Yin Chaoyou Fu Sirui Zhao Ke Li Xing Sun Tong Xu and Enhong Chen. 2024. A Survey on Multimodal Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2306.13549\u00a0[cs.CV]"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.05543 (2023).","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_61_1","unstructured":"Shihao Zhao Dongdong Chen Yen-Chun Chen Jianmin Bao Shaozhe Hao Lu Yuan and Kwan-Yee\u00a0K Wong. 2024. Uni-controlnet: All-in-one control to text-to-image diffusion models. Advances in Neural Information Processing Systems 36 (2024)."}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:59:20Z","timestamp":1774018760000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730615"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":60,"alternative-id":["10.1145\/3721238.3730615","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730615","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}