{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:35:39Z","timestamp":1778081739453,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:00:00Z","timestamp":1702166400000},"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":[[2023,12,10]]},"DOI":"10.1145\/3610548.3618208","type":"proceedings-article","created":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T12:28:40Z","timestamp":1702297720000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Anything to Glyph: Artistic Font Synthesis via Text-to-Image Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9970-191X","authenticated-orcid":false,"given":"Changshuo","family":"Wang","sequence":"first","affiliation":[{"name":"Shandong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3872-9062","authenticated-orcid":false,"given":"Lei","family":"Wu","sequence":"additional","affiliation":[{"name":"Shandong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3605-8206","authenticated-orcid":false,"given":"Xiaole","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3828-9834","authenticated-orcid":false,"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0273-5946","authenticated-orcid":false,"given":"Lei","family":"Meng","sequence":"additional","affiliation":[{"name":"Shandong Research Institute of Industrial Technology, China and Shandong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-5659","authenticated-orcid":false,"given":"Xiangxu","family":"Meng","sequence":"additional","affiliation":[{"name":"Shandong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01389"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Xu Chen Lei Wu 2021. MLFont: Few-Shot Chinese Font Generation via Deep Meta-Learning. In ICMR. 37\u201345.","DOI":"10.1145\/3460426.3463606"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"e_1_3_2_2_5_1","unstructured":"DeepFloydLab. 2023. Deepfloyd if. (2023). https:\/\/github.com\/deep-floyd\/IF"},{"key":"e_1_3_2_2_6_1","volume-title":"Conference and Workshop on Neural Information Processing Systems 34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Conference and Workshop on Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356574"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_2_10_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33 (2020), 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_11_1","unstructured":"Jonathan Ho and Tim Salimans. 2021. Classifier-Free Diffusion Guidance. (2021). https:\/\/openreview.net\/forum?id=qw8AKxfYbI"},{"key":"e_1_3_2_2_12_1","volume-title":"Word-as-image for semantic typography. arXiv preprint arXiv:2303.01818","author":"Iluz Shir","year":"2023","unstructured":"Shir Iluz, Yael Vinker, Amir Hertz, Daniel Berio, Daniel Cohen-Or, and Ariel Shamir. 2023. Word-as-image for semantic typography. arXiv preprint arXiv:2303.01818 (2023)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3145749.3149440"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Xiang Li Lei Wu Xu Chen Lei Meng and Xiangxu Meng. 2022. DSE-Net: Artistic Font Image Synthesis via Disentangled Style Encoding. In ICME. 1\u20136.","DOI":"10.1109\/ICME52920.2022.9859795"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/122"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_2_19_1","volume-title":"Fast Solver for Guided Sampling of Diffusion Probabilistic Models. arXiv preprint arXiv:2211.01095","author":"Cheng Lu","year":"2022","unstructured":"Cheng Lu 2022a. DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. arXiv preprint arXiv:2211.01095 (2022)."},{"key":"e_1_3_2_2_20_1","volume-title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps. 35","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan LI, and Jun Zhu. 2022b. DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps. 35 (2022), 5775\u20135787. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/260a14acce2a89dad36adc8eefe7c59e-Paper-Conference.pdf"},{"key":"e_1_3_2_2_21_1","volume-title":"Prompt-based multi-modal image segmentation. arXiv preprint arXiv:2112.10003","author":"L\u00fcddecke Timo","year":"2021","unstructured":"Timo L\u00fcddecke and Alexander\u00a0S Ecker. 2021. Prompt-based multi-modal image segmentation. arXiv preprint arXiv:2112.10003 (2021)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475724.3483600"},{"key":"e_1_3_2_2_23_1","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. (2022). https:\/\/openreview.net\/forum?id=aBsCjcPu_tE"},{"key":"e_1_3_2_2_24_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, 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_25_1","volume-title":"International Conference on Machine Learning. PMLR, 8162\u20138171","author":"Nichol Alexander\u00a0Quinn","year":"2021","unstructured":"Alexander\u00a0Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning. PMLR, 8162\u20138171."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"e_1_3_2_2_27_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv preprint arXiv: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. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Machine Learning. PMLR, 8748\u20138763","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, 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_2_29_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_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_31_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In MICCAI. Springer, 234\u2013241."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_2_2_33_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2021a. Denoising Diffusion Implicit Models. (2021). https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"e_1_3_2_2_34_1","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik\u00a0P Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2021b. Score-Based Generative Modeling through Stochastic Differential Equations. (2021). https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00132"},{"key":"e_1_3_2_2_36_1","volume-title":"Conference and Workshop on Neural Information Processing Systems 30","author":"Den\u00a0Oord Aaron Van","year":"2017","unstructured":"Aaron Van Den\u00a0Oord, Oriol Vinyals, 2017. Neural discrete representation learning. Conference and Workshop on Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"e_1_3_2_2_38_1","volume-title":"Pretraining is all you need for image-to-image translation. arXiv preprint arXiv:2205.12952","author":"Wang Tengfei","year":"2022","unstructured":"Tengfei Wang, Ting Zhang, Bo Zhang, Hao Ouyang, Dong Chen, Qifeng Chen, and Fang Wen. 2022. Pretraining is all you need for image-to-image translation. arXiv preprint arXiv:2205.12952 (2022)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00509"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011238"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055211"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00454"},{"key":"e_1_3_2_2_44_1","volume-title":"Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543","author":"Zhang Lvmin","year":"2023","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"SA '23: SIGGRAPH Asia 2023","location":"Sydney NSW Australia","acronym":"SA '23","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2023 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610548.3618208","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610548.3618208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:34:13Z","timestamp":1755768853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610548.3618208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,10]]},"references-count":45,"alternative-id":["10.1145\/3610548.3618208","10.1145\/3610548"],"URL":"https:\/\/doi.org\/10.1145\/3610548.3618208","relation":{},"subject":[],"published":{"date-parts":[[2023,12,10]]},"assertion":[{"value":"2023-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}