{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:39:24Z","timestamp":1786120764023,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818463","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"8190-8201","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Pinterest Canvas: Large-Scale Image Generation at Pinterest"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0016-9100","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"first","affiliation":[{"name":"Pinterest, Inc., San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9397-2429","authenticated-orcid":false,"given":"Eric","family":"Tzeng","sequence":"additional","affiliation":[{"name":"Pinterest, Inc., San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6212-9073","authenticated-orcid":false,"given":"Raymond","family":"Shiau","sequence":"additional","affiliation":[{"name":"Pinterest, Inc., San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6549-9977","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"additional","affiliation":[{"name":"Pinterest, Inc., San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0271-2342","authenticated-orcid":false,"given":"Dmitry","family":"Kislyuk","sequence":"additional","affiliation":[{"name":"Pinterest, Inc., San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9664-8644","authenticated-orcid":false,"given":"Charles","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Pinterest, Inc., San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Alimama Creative. 2024. EcomXL ControlNet Inpaint. https:\/\/huggingface.co\/ alimama-creative\/EcomXL_controlnet_inpaint"},{"key":"e_1_3_2_1_2_1","unstructured":"Alimama Creative. 2024. FLUX ControlNet Inpainting. https:\/\/github.com\/alimama-creative\/FLUX-Controlnet-Inpainting"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737253"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of The ACM Web Conference 2026 (TheWebConf '26)","author":"Beal Josh","year":"2026","unstructured":"Josh Beal, Eric Kim, Jinfeng Rao, RexWu, Dmitry Kislyuk, and Charles Rosenberg. 2026. PinCLIP: Large-scale Foundational Multimodal Representation at Pinterest. In Proceedings of The ACM Web Conference 2026 (TheWebConf '26). ACM, Dubai, United Arab Emirates, 9 pages. https:\/\/www.pinterestcareers.com\/media\/ eoqd5wcs\/pinclip.pdf"},{"key":"e_1_3_2_1_5_1","unstructured":"Black Forest Labs. 2024. FLUX.1. https:\/\/github.com\/black-forest-labs\/flux"},{"key":"e_1_3_2_1_6_1","unstructured":"Black Forest Labs. 2025. FLUX.2: Analyzing and Enhancing the Latent Space of FLUX - Representation Comparison. https:\/\/bfl.ai\/research\/representationcomparison"},{"key":"e_1_3_2_1_7_1","volume-title":"Efros","author":"Brooks Tim","year":"2023","unstructured":"Tim Brooks, Aleksander Holynski, and Alexei A. Efros. 2023. InstructPix2Pix: Learning to Follow Image Editing Instructions. arXiv:2211.09800 [cs.CV] https: \/\/arxiv.org\/abs\/2211.09800"},{"key":"e_1_3_2_1_8_1","unstructured":"Patrick Esser Sumith Kulal Andreas Blattmann Rahim Entezari Jonas M\u00fcller Harry Saini Yam Levi Dominik Lorenz Axel Sauer Frederic Boesel Dustin Podell Tim Dockhorn Zion English Kyle Lacey Alex Goodwin Yannik Marek and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. arXiv:2403.03206 [cs.CV] https:\/\/arxiv.org\/abs\/2403.03206"},{"key":"e_1_3_2_1_9_1","volume-title":"Zengqi Xun, Chengyue Sun, Rongfei Jia, Binqiang Zhao, and Hao Zhang.","author":"Fu Huan","year":"2021","unstructured":"Huan Fu, Bowen Cai, Lin Gao, Lingxiao Zhang, JiamingWang Cao Li, Zengqi Xun, Chengyue Sun, Rongfei Jia, Binqiang Zhao, and Hao Zhang. 2021. 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics. arXiv:2011.09127 [cs.CV] https:\/\/arxiv.org\/abs\/2011.09127"},{"key":"e_1_3_2_1_10_1","unstructured":"Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit H. Bermano Gal Chechik and Daniel Cohen-Or. 2022. An Image isWorth OneWord: Personalizing Text-to-Image Generation using Textual Inversion. arXiv:2208.01618 [cs.CV] https:\/\/arxiv.org\/abs\/2208.01618"},{"key":"e_1_3_2_1_11_1","unstructured":"Google. 2025. Nano Banana. https:\/\/deepmind.google\/models\/gemini-image\/ flash"},{"key":"e_1_3_2_1_12_1","volume-title":"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. International Conference on Learning Representations (2024)."},{"key":"e_1_3_2_1_13_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. arXiv:2006.11239 [cs.LG] https:\/\/arxiv.org\/abs\/2006.11239"},{"key":"e_1_3_2_1_14_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_15_1","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:2106.09685 [cs.CL] https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Miika Aittala Jaakko Lehtinen Janne Hellsten Timo Aila and Samuli Laine. 2024. Analyzing and Improving the Training Dynamics of Diffusion Models. arXiv:2312.02696 [cs.CV] https:\/\/arxiv.org\/abs\/2312.02696","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"e_1_3_2_1_17_1","unstructured":"Taehun Kim Kunhee Kim Joonyeong Lee Dongmin Cha Jiho Lee and Daijin Kim. 2022. Revisiting Image Pyramid Structure for High Resolution Salient Object Detection. arXiv:2209.09475 [cs.CV] https:\/\/arxiv.org\/abs\/2209.09475"},{"key":"e_1_3_2_1_18_1","unstructured":"Black Forest Labs Stephen Batifol Andreas Blattmann Frederic Boesel Saksham Consul Cyril Diagne Tim Dockhorn Jack English Zion English Patrick Esser Sumith Kulal Kyle Lacey Yam Levi Cheng Li Dominik Lorenz Jonas M\u00fcller Dustin Podell Robin Rombach Harry Saini Axel Sauer and Luke Smith. 2025. FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space. arXiv:2506.15742 [cs.GR] https:\/\/arxiv.org\/abs\/2506.15742"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32496"},{"key":"e_1_3_2_1_20_1","unstructured":"Shanchuan Lin Bingchen Liu Jiashi Li and Xiao Yang. 2024. Common Diffusion Noise Schedules and Sample Steps are Flawed. arXiv:2305.08891 [cs.CV] https: \/\/arxiv.org\/abs\/2305.08891"},{"key":"e_1_3_2_1_21_1","unstructured":"Yaron Lipman Ricky T. Q. Chen Heli Ben-Hamu Maximilian Nickel and Matt Le. 2023. Flow Matching for Generative Modeling. arXiv:2210.02747 [cs.LG] https:\/\/arxiv.org\/abs\/2210.02747"},{"key":"e_1_3_2_1_22_1","unstructured":"Open AI. 2025. GPT-Image. https:\/\/platform.openai.com\/docs\/guides\/imagegeneration"},{"key":"e_1_3_2_1_23_1","unstructured":"William Peebles and Saining Xie. 2023. Scalable Diffusion Models with Transformers. arXiv:2212.09748 [cs.CV] https:\/\/arxiv.org\/abs\/2212.09748"},{"key":"e_1_3_2_1_24_1","volume-title":"Training a Commercial-Level Video Generation Model in 200k. arXiv preprint arXiv:2503.09642","author":"Peng Xiangyu","year":"2025","unstructured":"Xiangyu Peng, Zangwei Zheng, Chenhui Shen, Tom Young, Xinying Guo, Binluo Wang, Hang Xu, Hongxin Liu, Mingyan Jiang, Wenjun Li, Yuhui Wang, Anbang Ye, Gang Ren, QianranMa,Wanying Liang, Xiang Lian, XiwenWu, Yuting Zhong, Zhuangyan Li, Chaoyu Gong, Guojun Lei, Leijun Cheng, Limin Zhang, Minghao Li, Ruijie Zhang, Silan Hu, Shijie Huang, Xiaokang Wang, Yuanheng Zhao, Yuqi Wang, Ziang Wei, and Yang You. 2025. Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k. arXiv preprint arXiv:2503.09642 (2025)."},{"key":"e_1_3_2_1_25_1","unstructured":"Pinterest. [n.d.]. Pinterest Performance. https:\/\/business.pinterest.com\/pinterest-performance-plus\/."},{"key":"e_1_3_2_1_26_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. arXiv:2112.10752 [cs.CV] https:\/\/arxiv.org\/abs\/2112.10752","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","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. arXiv:2208.12242 [cs.CV] https:\/\/arxiv.org\/abs\/2208.12242","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_28_1","volume-title":"Palette: Image-to-Image Diffusion Models. arXiv:2111.05826 [cs.CV] https:\/\/arxiv.org\/abs\/2111.05826","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Huiwen Chang, Chris A. Lee, Jonathan Ho, Tim Salimans, David J. Fleet, and Mohammad Norouzi. 2022. Palette: Image-to-Image Diffusion Models. arXiv:2111.05826 [cs.CV] https:\/\/arxiv.org\/abs\/2111.05826"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik P. Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2021. Score-Based Generative Modeling through Stochastic Differential Equations. arXiv:2011.13456 [cs.LG] https:\/\/arxiv.org\/abs\/2011. 13456","DOI":"10.1155\/2011\/613695"},{"key":"e_1_3_2_1_30_1","volume-title":"RoFormer: Enhanced Transformer with Rotary Position Embedding. arXiv preprint arXiv:2104.09864","author":"Su Jianlin","year":"2021","unstructured":"Jianlin Su, Yu Lu, Shengfeng Pan, Ahmed Murtadha, Bo Wen, and Yunfeng Liu. 2021. RoFormer: Enhanced Transformer with Rotary Position Embedding. arXiv preprint arXiv:2104.09864 (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Keyu Tian Yi Jiang Zehuan Yuan Bingyue Peng and Liwei Wang. 2024. Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction. arXiv:2404.02905 [cs.CV] https:\/\/arxiv.org\/abs\/2404.02905","DOI":"10.52202\/079017-2694"},{"key":"e_1_3_2_1_32_1","volume-title":"Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:2503.20314","author":"Wan Team","year":"2025","unstructured":"Team Wan, Ang Wang, Baole Ai, Bin Wen, Chaojie Mao, Chen-Wei Xie, Di Chen, Feiwu Yu, Haiming Zhao, Jianxiao Yang, Jianyuan Zeng, Jiayu Wang, Jingfeng Zhang, Jingren Zhou, Jinkai Wang, Jixuan Chen, Kai Zhu, Kang Zhao, Keyu Yan, Lianghua Huang, Mengyang Feng, Ningyi Zhang, Pandeng Li, Pingyu Wu, Ruihang Chu, Ruili Feng, Shiwei Zhang, Siyang Sun, Tao Fang, Tianxing Wang, Tianyi Gui, Tingyu Weng, Tong Shen, Wei Lin, Wei Wang, Wei Wang, Wenmeng Zhou, Wente Wang, Wenting Shen, Wenyuan Yu, Xianzhong Shi, Xiaoming Huang, Xin Xu, Yan Kou, Yangyu Lv, Yifei Li, Yijing Liu, Yiming Wang, Yingya Zhang, Yitong Huang, Yong Li, You Wu, Yu Liu, Yulin Pan, Yun Zheng, Yuntao Hong, Yupeng Shi, Yutong Feng, Zeyinzi Jiang, Zhen Han, Zhi-Fan Wu, and Ziyu Liu. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:2503.20314 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"RoomEditor","author":"Wang Qilong","unstructured":"Qilong Wang, Xiaofan Ming, Zhenyi Lin, Jinwen Li, Dongwei Ren, Wangmeng Zuo, and Qinghua Hu. 2025. RoomEditor: A Parameter-Sharing Diffusion Architecture for High-Fidelity Furniture Synthesis. arXiv:2512.17573 [cs.CV] https:\/\/arxiv.org\/abs\/2512.17573"},{"key":"e_1_3_2_1_34_1","volume-title":"Yu Qiao, and Xiaoou Tang.","author":"Yu Ke","year":"2018","unstructured":"XintaoWang, Ke Yu, ShixiangWu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, and Xiaoou Tang. 2018. ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. arXiv:1809.00219 [cs.CV] https:\/\/arxiv.org\/ abs\/1809.00219"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Mitchell Wortsman Tim Dettmers Luke Zettlemoyer Ari Morcos Ali Farhadi and Ludwig Schmidt. 2023. Stable and low-precision training for large-scale vision-language models. arXiv:2304.13013 [cs.LG] https:\/\/arxiv.org\/abs\/2304. 13013","DOI":"10.52202\/075280-0451"},{"key":"e_1_3_2_1_36_1","unstructured":"Chenfei Wu Jiahao Li Jingren Zhou Junyang Lin Kaiyuan Gao Kun Yan Sheng ming Yin Shuai Bai Xiao Xu Yilei Chen Yuxiang Chen Zecheng Tang Zekai Zhang Zhengyi Wang An Yang Bowen Yu Chen Cheng Dayiheng Liu Deqing Li Hang Zhang Hao Meng HuWei Jingyuan Ni Kai Chen Kuan Cao Liang Peng Lin Qu Minggang Wu Peng Wang Shuting Yu Tingkun Wen Wensen Feng Xiaoxiao Xu Yi Wang Yichang Zhang Yongqiang Zhu Yujia Wu Yuxuan Cai and Zenan Liu. 2025. Qwen-Image Technical Report. arXiv:2508.02324 [cs.CV] https:\/\/arxiv.org\/abs\/2508.02324"},{"key":"e_1_3_2_1_37_1","unstructured":"Keming Wu Sicong Jiang Max Ku Ping Nie Minghao Liu and Wenhu Chen. 2025. EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing. arXiv:2509.26346 [cs.CV] https:\/\/arxiv.org\/abs\/2509.26346"},{"key":"e_1_3_2_1_38_1","unstructured":"Katherine Xu Lingzhi Zhang and Jianbo Shi. 2025. Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models. arXiv:2405.14828 [cs.CV] https:\/\/arxiv.org\/abs\/2405.14828"},{"key":"e_1_3_2_1_39_1","volume-title":"Meng Wymond Wu, and Mingming Sun","author":"Yang Jinze","year":"2024","unstructured":"Jinze Yang, Haoran Wang, Zining Zhu, Chenglong Liu, Meng Wymond Wu, and Mingming Sun. 2024. VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model. arXiv:2406.01059 [cs.CV] https:\/\/arxiv.org\/abs\/2406.01059"},{"key":"e_1_3_2_1_40_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. arXiv:2308.06721 [cs.CV] https:\/\/arxiv.org\/abs\/2308.06721"},{"key":"e_1_3_2_1_41_1","volume-title":"Thang Luong, Gunjan Baid, ZiruiWang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, Ben Hutchinson, Wei Han, Zarana Parekh, Xin Li, Han Zhang, Jason Baldridge, and Yonghui Wu.","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, ZiruiWang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, Ben Hutchinson, Wei Han, Zarana Parekh, Xin Li, Han Zhang, Jason Baldridge, and Yonghui Wu. 2022. Scaling Autoregressive Models for Content-Rich Text-to-Image Generation. arXiv:2206.10789 [cs.CV] https:\/\/arxiv.org\/abs\/2206.10789"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Yu Zeng Vishal M. Patel HaochenWang Xun Huang Ting-ChunWang Ming-Yu Liu and Yogesh Balaji. 2024. JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation. arXiv:2407.06187 [cs.CV] https: \/\/arxiv.org\/abs\/2407.06187","DOI":"10.1109\/CVPR52733.2024.00648"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. arXiv:2302.05543 [cs.CV] https:\/\/arxiv.org\/abs\/2302.05543","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_44_1","unstructured":"Sijie Zhao Jing Cheng Yaoyao Wu Hao Xu and Shaohui Jiao. 2025. DreamPainter: Image Background Inpainting for E-commerce Scenarios. arXiv:2508.02155 [cs.CV] https:\/\/arxiv.org\/abs\/2508.02155"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:30:38Z","timestamp":1786066238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":44,"alternative-id":["10.1145\/3770855.3818463","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818463","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}