FusAIn: Composing Generative AI Visual Prompts Using Pen-based Interaction
Xiaohan Peng, Janin Koch, Wendy E. Mackay
Abstract
A pen-based GenAI visual prompt composition tool where designers use (1) Source panel for image search, upload, and display. They extract visual properties with "smart" pens from (2) Pen sets (object, color, texture, basic, eraser) and compose visual prompts on (3) Canvas with editing tools. They can add additional text prompts at (4) Text prompt area, and use (5) Brush scope visualizing pen status. (6) Generation modes include Guided Generate and Merge. The result appears in (7) Generation panel with style lock, and can be added to ( 8) Image gallery.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 6e5b182c-a132-4afe-9acb-a19f94ceb252Cited by top-tier papers5
- ImaginationVellum: Generative-AI Ideation Canvas with Spatial Prompts, Generative Strokes, and Ideation HistoryNicolai Marquardt, Asta Roseway, Hugo Romat, Payod Panda et al.UIST 2025 · 13 citations
- DesignTrace: Exploring, Iterating and Tracking Design Alternatives with GenAIXiaohan Peng, Debanjana Haldar, Wendy E. Mackay, Janin KochCHI 2026 · 3 citations
- Component-Wise Sketching and Generation for Car Interior DesignJeongche Yoon, Seung-Jun Lee, Donghyeok Ma, Seok-Hyung BaeCHI 2026 · 1 citation
- Preference-Guided Prompt Optimization for Text-to-Image GenerationZhipeng Li, Yi-Chi Liao, Christian HolzCHI 2026 · 1 citation
- MagicQuill V2: Precise and Interactive Image Editing with Layered Visual CuesZichen Liu, Yue Yu, Hao Ouyang, Qiuyu Wang et al.CVPR 2026
Builds on22
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- Why Johnny Can't Prompt: How Non-AI Experts Try (and Fail) to Design LLM PromptsJ. D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, Qian YangCHI 2023 · 892 citations
- Design Guidelines for Prompt Engineering Text-to-Image Generative ModelsVivian Liu, Lydia B. ChiltonCHI 2022 · 586 citations
- The Metacognitive Demands and Opportunities of Generative AILev Tankelevitch, Viktor Kewenig, Auste Simkute, Ava Elizabeth Scott et al.CHI 2024 · 279 citations
- What is Human-Centered about Human-Centered AI? A Map of the Research LandscapeTara Capel, Margot BreretonCHI 2023 · 218 citations
Related papers
- Interaction Methods in Generative AI Image Tools: A Review of Trends and Design Opportunities Across HCI and IndustryHyerim Park, Malin Eiband, André Luckow, Michael SedlmairCHI 2026 · 2 citations
- The Impact of Sketch-guided vs. Prompt-guided 3D Generative AIs on the Design Exploration ProcessSeung Won Lee, Tae Hee Jo, Semin Jin, Jiin Choi et al.CHI 2024 · 48 citations
- GenQuery: Supporting Expressive Visual Search with Generative ModelsKihoon Son, DaEun Choi, Tae Soo Kim, Young-Ho Kim et al.CHI 2024 · 48 citations
- DesignWeaver: Dimensional Scaffolding for Text-to-Image Product DesignSirui Tao, Ivan Liang, Cindy Peng, Zhiqing Wang et al.CHI 2025 · 19 citations
- When Teams Embrace AI: Human Collaboration Strategies in Generative Prompting in a Creative Design TaskYuanning Han, Ziyi Qiu, Jiale Cheng, Ray LCCHI 2024 · 103 citations
