RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions
Yunlong Wang, Shuyuan Shen, Brian Y. Lim

TL;DR
RePrompt is an automatic prompt editing method that refines text prompts to enhance the emotional expressiveness of AI-generated images, especially improving the depiction of negative emotions.
Contribution
The paper introduces RePrompt, a novel automatic prompt refinement technique that uses proxy models and curated features to improve emotional accuracy in AI-generated images.
Findings
RePrompt significantly improves emotional expressiveness in generated images.
The method is particularly effective for negative emotions.
User studies confirm enhanced emotional alignment with input texts.
Abstract
Generative AI models have shown impressive ability to produce images with text prompts, which could benefit creativity in visual art creation and self-expression. However, it is unclear how precisely the generated images express contexts and emotions from the input texts. We explored the emotional expressiveness of AI-generated images and developed RePrompt, an automatic method to refine text prompts toward precise expression of the generated images. Inspired by crowdsourced editing strategies, we curated intuitive text features, such as the number and concreteness of nouns, and trained a proxy model to analyze the feature effects on the AI-generated image. With model explanations of the proxy model, we curated a rubric to adjust text prompts to optimize image generation for precise emotion expression. We conducted simulation and user studies, which showed that RePrompt significantly…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
