Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tao, Sirui, Liang, Ivan, Peng, Cindy, Wang, Zhiqing, Palani, Srishti, Dow, Steven P.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2502.09867
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910076317466624
author Tao, Sirui
Liang, Ivan
Peng, Cindy
Wang, Zhiqing
Palani, Srishti
Dow, Steven P.
author_facet Tao, Sirui
Liang, Ivan
Peng, Cindy
Wang, Zhiqing
Palani, Srishti
Dow, Steven P.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09867
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design
Tao, Sirui
Liang, Ivan
Peng, Cindy
Wang, Zhiqing
Palani, Srishti
Dow, Steven P.
Human-Computer Interaction
Artificial Intelligence
H.5.2
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.
title DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design
topic Human-Computer Interaction
Artificial Intelligence
H.5.2
url https://arxiv.org/abs/2502.09867