DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design

Computer Science > Human-Computer Interaction [Submitted on 14 Feb 2025 (v1), last revised 20 Feb 2025 (this version, v2)] DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design Sirui Tao, Ivan Liang, Cindy Peng, Zhiqing Wang, Srishti Palani, Steven P. Dow Generative AI has enabled novice designers to quickly create professional-looking visual representations for product concepts. However, novices have limited domain knowledge that could constrain their ability to write prompts that effectively explore a product design space. To understand how experts explore and communicate about design spaces, we conducted a formative study with 12 experienced product designers and found that experts -- and their less-versed clients -- often use visual references to guide co-design discussions rather than written descriptions. These insights inspired DesignWeaver, an interface that helps novices generate prompts for a text-to-image model by surfacing key product design dimensions from generated images into a palette for quick selection. In a study with 52 novices, DesignWeaver enabled participants to craft longer prompts with more domain-specific vocabularies, resulting in more diverse, innovative product designs. However, the nuanced prompts heightened participants' expectations beyond what current text-to-image models could deliver. We discuss implications for AI-based product design support tools. Comments: 26 pages, 22 figures, CHI 2025 Subjects: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) ACM classes: H.5.2 Cite as: arXiv:2502.09867 [cs.HC]   (or arXiv:2502.09867v2 [cs.HC] for this version)   https://doi.org/10.48550/arXiv.2502.09867 Focus to learn more Related DOI: https://doi.org/10.1145/3706598.3714211 Focus to learn more Submission history From: Sirui Tao [view email] [v1] Fri, 14 Feb 2025 02:33:41 UTC (95,659 KB) [v2] Thu, 20 Feb 2025 01:56:16 UTC (95,660 KB) Access Paper: HTML (experimental) view license Current browse context: cs.HC < prev   |   next > new | recent | 2025-02 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)