Is It AI or Is It Me? Understanding Users' Prompt Journey with Text-to-Image Generative AI Tools
Atefeh Mahdavi Goloujeh, Anne Sullivan, Brian Magerko
摘要
Generative Artificial Intelligence (AI) has witnessed unprecedented growth in text-to-image AI tools. Yet, much remains unknown about users’ prompt journey with such tools in the wild. In this paper, we posit that designing human-centered text-to-image AI tools requires a clear understanding of how individuals intuitively approach crafting prompts, and what challenges they may encounter. To address this, we conducted semi-structured interviews with 19 existing users of a text-to-image AI tool. Our findings (1) offer insights into users’ prompt journey including structures and processes for writing, evaluating, and refining prompts in text-to-image AI tools and (2) indicate that users must overcome barriers to aligning AI to their intents, and mastering prompt crafting knowledge. From the findings, we discuss the prompt journey as an individual yet a social experience and highlight opportunities for aligning text-to-image AI tools and users’ intents.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
引用它的顶会 Paper20
- AIdeation: Designing a Human-AI Collaborative Ideation System for Concept DesignersWen-Fan Wang, Chien-Ting Lu, Nil Ponsa Campanyà, Bing-Yu Chen 等CHI 2025 · 被引用 46 次
- Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI LiteratureShuning Zhang, Hui Wang, Xin YiCSCW 2025 · 被引用 31 次
- AI-Instruments: Embodying Prompts as Instruments to Abstract & Reflect Graphical Interface Commands as General-Purpose ToolsNathalie Riche, Anna Offenwanger, Frederic Gmeiner, David Brown 等CHI 2025 · 被引用 26 次
- Brickify: Enabling Expressive Design Intent Specification through Direct Manipulation on Design TokensXinyu Shi, Yinghou Wang, Ryan A. Rossi, Jian ZhaoCHI 2025 · 被引用 18 次
- Paratrouper: Exploratory Creation of Character Cast Visuals Using Generative AIJoanne Leong, David Ledo, Thomas Driscoll, Tovi Grossman 等CHI 2025 · 被引用 16 次
相关 Paper
- Understanding User Perceptions and the Role of AI Image Generators in Image Creation WorkflowsShu-Jung Han, Susan R. FussellCHI 2025 · 被引用 10 次
- DesignWeaver: Dimensional Scaffolding for Text-to-Image Product DesignSirui Tao, Ivan Liang, Cindy Peng, Zhiqing Wang 等CHI 2025 · 被引用 19 次
- GeneyMAP: Exploring the Potential of GenAI to Facilitate Mapping User Journeys for UX DesignYihan Mei, Zhao Wu, Junnan Yu, Wenan Li 等CHI 2025 · 被引用 12 次
- Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language ModelsStephen Brade, Bryan Wang, Maurício Sousa, Sageev Oore 等UIST 2023 · 被引用 179 次
- Proactive Agents for Multi-Turn Text-to-Image Generation Under UncertaintyMeera Hahn, Wenjun Zeng, Nithish Kannen, Rich Galt 等ICML 2025
