📝 SummarXiv

Abstract

Generative AI opens new possibilities for design exploration by rapidly generating images aligned with user goals. However, our formative study (N=7) revealed two key challenges that limit broad and efficient exploration with these models: the lack of expressive channels for articulating exploratory directions and ranges, and insufficient support for reusing past intents. We present IdeaBlocks, where users can modularize exploratory intents into Exploration Blocks, capturing property, direction, and range of exploration. Users can reuse prior intents at multiple levels (block, path, and project) with options for literal or context-adaptive reuse. In our comparative study (N=12), participants using IdeaBlocks explored 2.13 times more images with 12.5% greater visual diversity than the baseline, demonstrating how structured intent expression and reuse support more effective exploration. A three-day deployment study (N=6) further revealed how different reuse units and mechanisms enabled distinct creative strategies, offering design implications for future intent-aware creativity support systems.