RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions

要旨

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 improves the emotional expressiveness of AI-generated images, especially for negative emotions.

著者
Yunlong Wang
National University of Singapore, Singapore, Singapore
Shuyuan Shen
National University of Singapore, Singapore, Singapore
Brian Y. Lim
National University of Singapore, Singapore, Singapore
論文URL

https://doi.org/10.1145/3544548.3581402

動画

会議: CHI 2023

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2023.acm.org/)

セッション: AI for Visual Generation

Room Y05+Y06
6 件の発表
2023-04-26 20:10:00
2023-04-26 21:35:00