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

02/19/2023
by   Yunlong Wang, et al.
0

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.

READ FULL TEXT

page 2

page 11

page 18

research
04/26/2023

A Portrait of Emotion: Empowering Self-Expression through AI-Generated Art

We investigated the potential and limitations of generative artificial i...
research
06/22/2020

Facial Expression Editing with Continuous Emotion Labels

Recently deep generative models have achieved impressive results in the ...
research
12/21/2022

Computer says "No": The Case Against Empathetic Conversational AI

Emotions are an integral part of human cognition and they guide not only...
research
06/01/2022

When happy accidents spark creativity: Bringing collaborative speculation to life with generative AI

Generative AI techniques like those that synthesize images from text (te...
research
03/22/2023

The Prompt Artists

This paper examines the art practices, artwork, and motivations of proli...
research
06/20/2021

Challenges in Translation of Emotions in Multilingual User-Generated Content: Twitter as a Case Study

Although emotions are universal concepts, transferring the different sha...
research
09/30/2021

AffectGAN: Affect-Based Generative Art Driven by Semantics

This paper introduces a novel method for generating artistic images that...

Please sign up or login with your details

Forgot password? Click here to reset