PromptMap: An Alternative Interaction Style for AI-Based Image Generation
This work addresses the problem of prompt crafting for novice users in text-to-image AI, offering an incremental improvement in user interaction.
The paper tackled the difficulty novice users face in crafting effective prompts for AI-based image generation by developing PromptMap, an interaction style that groups images by semantic similarity in a map-like view, and found in a study with 60 participants that it supported users in crafting prompts by providing examples.
Recent technological advances popularized the use of image generation among the general public. Crafting effective prompts can, however, be difficult for novice users. To tackle this challenge, we developed PromptMap, a new interaction style for text-to-image AI that allows users to freely explore a vast collection of synthetic prompts through a map-like view with semantic zoom. PromptMap groups images visually by their semantic similarity, allowing users to discover relevant examples. We evaluated PromptMap in a between-subject online study ($n=60$) and a qualitative within-subject study ($n=12$). We found that PromptMap supported users in crafting prompts by providing them with examples. We also demonstrated the feasibility of using LLMs to create vast example collections. Our work contributes a new interaction style that supports users unfamiliar with prompting in achieving a satisfactory image output.