PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation
This addresses the problem of prompt ambiguity for users of generative text-to-image models, though it is incremental as it builds on existing models and datasets.
The researchers tackled the challenge of crafting effective prompts for text-to-image models by developing PromptMagician, an interactive visual analysis system that recommends keywords and visualizes results, with user studies showing it improves prompt engineering and creativity support.
Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts. However, developing effective prompts for desired images can be challenging due to the complexity and ambiguity of natural language. This research proposes PromptMagician, a visual analysis system that helps users explore the image results and refine the input prompts. The backbone of our system is a prompt recommendation model that takes user prompts as input, retrieves similar prompt-image pairs from DiffusionDB, and identifies special (important and relevant) prompt keywords. To facilitate interactive prompt refinement, PromptMagician introduces a multi-level visualization for the cross-modal embedding of the retrieved images and recommended keywords, and supports users in specifying multiple criteria for personalized exploration. Two usage scenarios, a user study, and expert interviews demonstrate the effectiveness and usability of our system, suggesting it facilitates prompt engineering and improves the creativity support of the generative text-to-image model.