{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:20:11Z","timestamp":1790623211270,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":89,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"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":[[2023,7,10]]},"DOI":"10.1145\/3563657.3596098","type":"proceedings-article","created":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T21:19:40Z","timestamp":1688937580000},"page":"1955-1977","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":150,"title":["3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5328-0120","authenticated-orcid":false,"given":"Vivian","family":"Liu","sequence":"first","affiliation":[{"name":"Autodesk Research, Canada and Columbia University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5185-7686","authenticated-orcid":false,"given":"Jo","family":"Vermeulen","sequence":"additional","affiliation":[{"name":"Autodesk Research, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2834-7757","authenticated-orcid":false,"given":"George","family":"Fitzmaurice","sequence":"additional","affiliation":[{"name":"Autodesk Research, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2680-2645","authenticated-orcid":false,"given":"Justin","family":"Matejka","sequence":"additional","affiliation":[{"name":"Autodesk Research, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","unstructured":"Saleema Amershi Kori Inkpen Jaime Teevan Ruth Kikin-Gil Eric Horvitz Dan Weld Mihaela Vorvoreanu Adam Fourney Besmira Nushi Penny Collisson Jina Suh Shamsi Iqbal and Paul Bennett. 2019. Guidelines for Human-AI Interaction. 1\u201313. https:\/\/doi.org\/10.1145\/3290605.3300233","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_3_2_2_2_1","volume-title":"https:\/\/knowledge.autodesk.com\/community\/screencast Retrieved","author":"Screencast Autodesk","year":"2022","unstructured":"Autodesk. 2022. Autodesk Screencast. https:\/\/knowledge.autodesk.com\/community\/screencast Retrieved September 15, 2022."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.destud.2015.08.001"},{"key":"e_1_3_2_2_4_1","unstructured":"Gwern Branwen. 2020. Gpt-3 creative fiction. https:\/\/www.gwern.net\/GPT-3"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","unstructured":"Tom\u00a0B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel\u00a0M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. https:\/\/doi.org\/10.48550\/ARXIV.2005.14165","DOI":"10.48550\/ARXIV.2005.14165"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","unstructured":"Miles Brundage Shahar Avin Jasmine Wang Haydn Belfield Gretchen Krueger Gillian Hadfield Heidy Khlaaf Jingying Yang Helen Toner Ruth Fong Tegan Maharaj Pang\u00a0Wei Koh Sara Hooker Jade Leung Andrew Trask Emma Bluemke Jonathan Lebensold Cullen O\u2019Keefe Mark Koren Th\u00e9o Ryffel JB Rubinovitz Tamay Besiroglu Federica Carugati Jack Clark Peter Eckersley Sarah de Haas Maritza Johnson Ben Laurie Alex Ingerman Igor Krawczuk Amanda Askell Rosario Cammarota Andrew Lohn David Krueger Charlotte Stix Peter Henderson Logan Graham Carina Prunkl Bianca Martin Elizabeth Seger Noa Zilberman Se\u00e1n\u00a0\u00d3 h\u00c9igeartaigh Frens Kroeger Girish Sastry Rebecca Kagan Adrian Weller Brian Tse Elizabeth Barnes Allan Dafoe Paul Scharre Ariel Herbert-Voss Martijn Rasser Shagun Sodhani Carrick Flynn Thomas\u00a0Krendl Gilbert Lisa Dyer Saif Khan Yoshua Bengio and Markus Anderljung. 2020. Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims. https:\/\/doi.org\/10.48550\/ARXIV.2004.07213","DOI":"10.48550\/ARXIV.2004.07213"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","unstructured":"Angel\u00a0X. Chang Mihail Eric Manolis Savva and Christopher\u00a0D. Manning. 2017. SceneSeer: 3D Scene Design with Natural Language. https:\/\/doi.org\/10.48550\/ARXIV.1703.00050","DOI":"10.48550\/ARXIV.1703.00050"},{"key":"e_1_3_2_2_8_1","volume-title":"Workflow Graphs: A Computational Model of Collective Task Strategies for 3D Design Software. In Graphics Interface","author":"Chang Minsuk","year":"2020","unstructured":"Minsuk Chang, Ben Lafreniere, Juho Kim, George Fitzmaurice, and Tovi Grossman. 2020. Workflow Graphs: A Computational Model of Collective Task Strategies for 3D Design Software. In Graphics Interface 2020. https:\/\/openreview.net\/forum?id=qXEzq5agzIN"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501988.2502008"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501988.2502008"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","unstructured":"Erin Cherry and Celine Latulipe. 2009. The creativity support index. 4009\u20134014. https:\/\/doi.org\/10.1145\/1520340.1520609","DOI":"10.1145\/1520340.1520609"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","unstructured":"Jaemin Cho Abhay Zala and Mohit Bansal. 2022. DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generative Transformers. https:\/\/doi.org\/10.48550\/ARXIV.2202.04053","DOI":"10.48550\/ARXIV.2202.04053"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","unstructured":"Bob Coyne and Richard Sproat. 2022. WordsEye: an automatic text-to-scene conversion system. https:\/\/doi.org\/10.1145\/383259.383316","DOI":"10.1145\/383259.383316"},{"key":"e_1_3_2_2_14_1","unstructured":"Katherine Crowson. 2021. afiaka87\/clip-guided-diffusion: A CLI tool\/python module for generating images from text using guided diffusion and CLIP from OpenAI.https:\/\/github.com\/afiaka87\/clip-guided-diffusion"},{"key":"e_1_3_2_2_15_1","unstructured":"Katherine Crowson. 2021. Rivers Have Wings. https:\/\/twitter.com\/RiversHaveWings"},{"key":"e_1_3_2_2_16_1","volume-title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance. arXiv preprint arXiv:2204.08583","author":"Crowson Katherine","year":"2022","unstructured":"Katherine Crowson, Stella Biderman, Daniel Kornis, Dashiell Stander, Eric Hallahan, Louis Castricato, and Edward Raff. 2022. VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance. arXiv preprint arXiv:2204.08583 (2022)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","unstructured":"Boris Dayma Suraj Patil Pedro Cuenca Khalid Saifullah Tanishq Abraham Ph\u00fac Le\u00a0Khac Luke Melas and Ritobrata Ghosh. 2021. DALLE Mini. https:\/\/doi.org\/10.5281\/zenodo.1234","DOI":"10.5281\/zenodo.1234"},{"key":"e_1_3_2_2_18_1","unstructured":"Manoj Deshpande Eric Sauda and Mary\u00a0Lou Maher. 2020. Towards Co-Build: An Architecture Machine for Co-Creative Form-Making."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3524073"},{"key":"e_1_3_2_2_20_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv:1810.04805\u00a0[cs.CL]","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv:1810.04805\u00a0[cs.CL]"},{"key":"e_1_3_2_2_21_1","unstructured":"Alaa El-Nouby Shikhar Sharma Hannes Schulz R\u00a0Devon Hjelm Layla El\u00a0Asri Samira\u00a0Ebrahimi Kahou Y. Bengio and Graham Taylor. 2018. Keep Drawing It: Iterative language-based image generation and editing."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","unstructured":"Patrick Esser Robin Rombach and Bj\u00f6rn Ommer. 2020. Taming Transformers for High-Resolution Image Synthesis. https:\/\/doi.org\/10.48550\/ARXIV.2012.09841","DOI":"10.48550\/ARXIV.2012.09841"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015775"},{"key":"e_1_3_2_2_24_1","unstructured":"Oran Gafni Adam Polyak Oron Ashual Shelly Sheynin Devi Parikh and Yaniv Taigman. 2022. Greater Creative Control for AI image generation. https:\/\/ai.facebook.com\/blog\/greater-creative-control-for-ai-image-generation\/"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.48550\/ARXIV.2208.01618","DOI":"10.48550\/ARXIV.2208.01618"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807478"},{"key":"e_1_3_2_2_27_1","unstructured":"Songwei Ge and Devi Parikh. 2021. Visual Conceptual Blending with Large-scale Language and Vision Models. arxiv:2106.14127\u00a0[cs.CL]"},{"key":"e_1_3_2_2_28_1","volume-title":"Gero and Mary\u00a0Lou Maher","author":"S.","year":"1993","unstructured":"John\u00a0S. Gero and Mary\u00a0Lou Maher. 1993. Modeling Creativity and Knowledge-Based Creative Design."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376316"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2110.07640"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Arnab Ghosh Richard Zhang Puneet\u00a0K. Dokania Oliver Wang Alexei\u00a0A. Efros Philip H.\u00a0S. Torr and Eli Shechtman. 2019. Interactive Sketch and Fill: Multiclass Sketch-to-Image Translation. arxiv:1909.11081\u00a0[cs.CV]","DOI":"10.1109\/ICCV.2019.00126"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866054"},{"key":"e_1_3_2_2_33_1","volume-title":"Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research. Advances in psychology 52","author":"Hart G.","year":"1988","unstructured":"S.\u00a0G. Hart and Lowell\u00a0E. Staveland. 1988. Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research. Advances in psychology 52 (1988), 139\u2013183."},{"key":"e_1_3_2_2_34_1","volume-title":"Defining Expertise in the Use of Constraint-based CAD Tools by Examining Practicing Professionals. Engineering Design Graphics Journal 69","author":"Hartman W.","year":"2004","unstructured":"Nathan\u00a0W. Hartman. 2004. Defining Expertise in the Use of Constraint-based CAD Tools by Examining Practicing Professionals. Engineering Design Graphics Journal 69 (2004)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468013.3468340"},{"key":"e_1_3_2_2_36_1","unstructured":"Autodesk Inc.2022. Autodesk Fusion 360 faster performance and quality of life updates. https:\/\/www.autodesk.com\/products\/fusion-360\/blog\/usability-and-performance-improvements-fusion-360\/"},{"key":"e_1_3_2_2_37_1","unstructured":"Autodesk Inc.2022. Fusion 360. https:\/\/help.autodesk.com\/view\/fusion360\/ENU\/?guid=GUID-7B5A90C8-E94C-48DA-B16B-430729B734DC"},{"key":"e_1_3_2_2_38_1","unstructured":"Autodesk Inc.2022. Generative design for manufacturing with Fusion 360. https:\/\/www.autodesk.com\/solutions\/generative-design\/manufacturing"},{"key":"e_1_3_2_2_39_1","volume-title":"Recognition of Science, and Technology (FIRST)","author":"Inspiration For","year":"2022","unstructured":"For Inspiration, Recognition of Science, and Technology (FIRST). 2022. FIRST Robotics Competition. https:\/\/www.firstinspires.org\/robotics\/frc"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Ajay Jain Ben Mildenhall Jonathan\u00a0T. Barron Pieter Abbeel and Ben Poole. 2022. Zero-Shot Text-Guided Object Generation with Dream Fields. (2022).","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445093"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","unstructured":"Ellen Jiang Kristen Olson Edwin Toh Alejandra Molina Aaron Donsbach Michael Terry and Carrie\u00a0J Cai. 2022. PromptMaker: Prompt-based Prototyping with Large Language Models. https:\/\/doi.org\/10.1145\/3491101.3503564","DOI":"10.1145\/3491101.3503564"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","unstructured":"Tero Karras Samuli Laine and Timo Aila. 2018. A Style-Based Generator Architecture for Generative Adversarial Networks. https:\/\/doi.org\/10.48550\/ARXIV.1812.04948","DOI":"10.48550\/ARXIV.1812.04948"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine Miika Aittala Janne Hellsten Jaakko Lehtinen and Timo Aila. 2020. Analyzing and Improving the Image Quality of StyleGAN. arxiv:1912.04958\u00a0[cs.CV]","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126662"},{"key":"e_1_3_2_2_46_1","volume-title":"Gesture and speech elicitation for 3D CAD modeling in conceptual design. Automation in Construction","author":"Khan Sumbul","year":"2019","unstructured":"Sumbul Khan and Bige Tun\u00e7er. 2019. Gesture and speech elicitation for 3D CAD modeling in conceptual design. Automation in Construction (2019)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1812.06216"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2012.02.004"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2021.05.093"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502030"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1080\/07370024.2020.1733576"},{"key":"e_1_3_2_2_52_1","unstructured":"Vivian Liu and Lydia\u00a0B. Chilton. 2021. Design Guidelines for Prompt Engineering Text-to-Image Generative Models. arxiv:2109.06977\u00a0[cs.HC]"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2204.09007"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","unstructured":"Maria\u00a0Teresa Llano Mark d\u2019Inverno Matthew Yee-King Jon McCormack Alon Ilsar Alison Pease and Simon Colton. 2022. Explainable Computational Creativity. (2022). https:\/\/doi.org\/10.48550\/ARXIV.2205.05682","DOI":"10.48550\/ARXIV.2205.05682"},{"key":"e_1_3_2_2_55_1","volume-title":"Cococo: AI-Steering Tools for Music Novices Co-Creating with Generative Models. In HAI-GEN+user2agent@IUI.","author":"Louie Ryan","year":"2020","unstructured":"Ryan Louie, Any Cohen, Cheng-Zhi\u00a0Anna Huang, Michael Terry, and Carrie\u00a0J. Cai. 2020. Cococo: AI-Steering Tools for Music Novices Co-Creating with Generative Models. In HAI-GEN+user2agent@IUI."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258887"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173943"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44150-022-00035-y"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","unstructured":"Ron Mokady Amir Hertz and Amit\u00a0H. Bermano. 2021. ClipCap: CLIP Prefix for Image Captioning. https:\/\/doi.org\/10.48550\/ARXIV.2111.09734","DOI":"10.48550\/ARXIV.2111.09734"},{"key":"e_1_3_2_2_61_1","unstructured":"Ryan Murdock. 2022. lucidrains\/big-sleep: A simple command line tool for text to image generation using OpenAI\u2019s CLIP and a BigGAN. Technique was originally created by https:\/\/twitter.com\/advadnoun. https:\/\/github.com\/lucidrains\/big-sleep"},{"key":"e_1_3_2_2_62_1","unstructured":"Ryan Murdock and Phil Wang. 2021. Big Sleep."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/344949.344959"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","unstructured":"Alex Nichol Heewoo Jun Prafulla Dhariwal Pamela Mishkin and Mark Chen. 2022. Point-E: A System for Generating 3D Point Clouds from Complex Prompts. https:\/\/doi.org\/10.48550\/ARXIV.2212.08751","DOI":"10.48550\/ARXIV.2212.08751"},{"key":"e_1_3_2_2_65_1","unstructured":"OpenAI. 2022. Dall\u00b7E: Introducing outpainting. https:\/\/openai.com\/blog\/dall-e-introducing-outpainting\/"},{"key":"e_1_3_2_2_66_1","unstructured":"Guy Parsons. 2022. The DALL-E 2 prompt book. https:\/\/dallery.gallery\/the-dalle-2-prompt-book\/"},{"key":"e_1_3_2_2_67_1","volume-title":"DreamFusion: Text-to-3D using 2D Diffusion. arXiv","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T. Barron, and Ben Mildenhall. 2022. DreamFusion: Text-to-3D using 2D Diffusion. arXiv (2022)."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3527927.3532792"},{"key":"e_1_3_2_2_69_1","volume-title":"Advances in Neural Information Processing Systems, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d'Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.). Vol.\u00a032. Curran Associates","author":"Qiao Tingting","year":"2019","unstructured":"Tingting Qiao, Jing Zhang, Duanqing Xu, and Dacheng Tao. 2019. Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge. In Advances in Neural Information Processing Systems, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d'Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.). Vol.\u00a032. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/d18f655c3fce66ca401d5f38b48c89af-Paper.pdf"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","unstructured":"Tingting Qiao Jing Zhang Duanqing Xu and Dacheng Tao. 2019. MirrorGAN: Learning Text-to-image Generation by Redescription. https:\/\/doi.org\/10.48550\/ARXIV.1903.05854","DOI":"10.48550\/ARXIV.1903.05854"},{"key":"e_1_3_2_2_71_1","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arxiv:2103.00020\u00a0[cs.CV]"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. https:\/\/doi.org\/10.48550\/ARXIV.2204.06125","DOI":"10.48550\/ARXIV.2204.06125"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"crossref","unstructured":"Laria Reynolds and Kyle McDonell. 2021. Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm. arxiv:2102.07350\u00a0[cs.CL]","DOI":"10.1145\/3411763.3451760"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2008.06.007"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_76_1","unstructured":"Kevin Roose. 2022. An A.I.-Generated Picture Won an Art Prize. Artists Aren\u2019t Happy. https:\/\/www.nytimes.com\/2022\/09\/02\/technology\/ai-artificial-intelligence-artists.html"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2205.11487"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","unstructured":"Aditya Sanghi Hang Chu Joseph\u00a0G. Lambourne Ye Wang Chin-Yi Cheng Marco Fumero and Kamal\u00a0Rahimi Malekshan. 2021. CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation. https:\/\/doi.org\/10.48550\/ARXIV.2110.02624","DOI":"10.48550\/ARXIV.2110.02624"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","unstructured":"Aditya Sanghi Rao Fu Vivian Liu Karl Willis Hooman Shayani Amir\u00a0Hosein Khasahmadi Srinath Sridhar and Daniel Ritchie. 2022. TextCraft: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Text. https:\/\/doi.org\/10.48550\/ARXIV.2211.01427","DOI":"10.48550\/ARXIV.2211.01427"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","unstructured":"Shikhar Sharma Dendi Suhubdy Vincent Michalski Samira\u00a0Ebrahimi Kahou and Yoshua Bengio. 2018. ChatPainter: Improving Text to Image Generation using Dialogue. https:\/\/doi.org\/10.48550\/ARXIV.1802.08216","DOI":"10.48550\/ARXIV.1802.08216"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511599"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445219"},{"key":"e_1_3_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459818"},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","unstructured":"Tongshuang Wu Ellen Jiang Aaron Donsbach Jeff Gray Alejandra Molina Michael Terry and Carrie\u00a0J Cai. 2022. PromptChainer: Chaining Large Language Model Prompts through Visual Programming. https:\/\/doi.org\/10.48550\/ARXIV.2203.06566","DOI":"10.48550\/ARXIV.2203.06566"},{"key":"e_1_3_2_2_85_1","doi-asserted-by":"publisher","unstructured":"Tongshuang Wu Michael Terry and Carrie\u00a0J Cai. 2022. AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts. https:\/\/doi.org\/10.1145\/3491102.3517582","DOI":"10.1145\/3491102.3517582"},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","unstructured":"Weihao Xia Yujiu Yang Jing-Hao Xue and Baoyuan Wu. 2020. TediGAN: Text-Guided Diverse Face Image Generation and Manipulation. https:\/\/doi.org\/10.48550\/ARXIV.2012.03308","DOI":"10.48550\/ARXIV.2012.03308"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964975"},{"key":"e_1_3_2_2_88_1","doi-asserted-by":"publisher","unstructured":"Tao Xu Pengchuan Zhang Qiuyuan Huang Han Zhang Zhe Gan Xiaolei Huang and Xiaodong He. 2017. AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks. https:\/\/doi.org\/10.48550\/ARXIV.1711.10485","DOI":"10.48550\/ARXIV.1711.10485"},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"publisher","unstructured":"Jiahui Yu Yuanzhong Xu Jing\u00a0Yu Koh Thang Luong Gunjan Baid Zirui Wang Vijay Vasudevan Alexander Ku Yinfei Yang Burcu\u00a0Karagol 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. https:\/\/doi.org\/10.48550\/ARXIV.2206.10789","DOI":"10.48550\/ARXIV.2206.10789"}],"event":{"name":"DIS '23: Designing Interactive Systems Conference","location":"Pittsburgh PA USA","acronym":"DIS '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2023 ACM Designing Interactive Systems Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563657.3596098","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3563657.3596098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:38:08Z","timestamp":1750163888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563657.3596098"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,10]]},"references-count":89,"alternative-id":["10.1145\/3563657.3596098","10.1145\/3563657"],"URL":"https:\/\/doi.org\/10.1145\/3563657.3596098","relation":{},"subject":[],"published":{"date-parts":[[2023,7,10]]},"assertion":[{"value":"2023-07-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}