PromptMap: An Alternative Interaction Style for AI-Based Image Generation
arXiv:2503.09436 · doi:10.1145/3708359.3712150
Abstract
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 () and a qualitative within-subject study (). 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.
Accepted to the 30th International Conference on Intelligent User Interfaces (IUI '25), March 24-27, 2025, Cagliari, Italy ; Link to code https://github.com/Bill2462/prompt-map
References in corpus (10)
- Adversarial Text-to-Image Synthesis: A Review
- A Taxonomy of Prompt Modifiers for Text-To-Image Generation
- Large-scale Text-to-Image Generation Models for Visual Artists' Creative Works
- Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation
- PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation
- RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions
- PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement
- Best Prompts for Text-to-Image Models and How to Find Them
- Optimizing Prompts for Text-to-Image Generation
- MiniCPM-V: A GPT-4V Level MLLM on Your Phone