Prompt Expansion for Adaptive Text-to-Image Generation

TL;DR

This paper introduces a Prompt Expansion framework that enhances text-to-image generation by producing diverse and high-quality images with less user effort, validated through human evaluations.

Contribution

It presents a novel Prompt Expansion model that optimizes expanded prompts to improve image diversity and quality in text-to-image generation.

Findings

Expanded prompts lead to more diverse images

Generated images are more aesthetically pleasing

Human evaluations favor the proposed method

Abstract

Text-to-image generation models are powerful but difficult to use. Users craft specific prompts to get better images, though the images can be repetitive. This paper proposes a Prompt Expansion framework that helps users generate high-quality, diverse images with less effort. The Prompt Expansion model takes a text query as input and outputs a set of expanded text prompts that are optimized such that when passed to a text-to-image model, generates a wider variety of appealing images. We conduct a human evaluation study that shows that images generated through Prompt Expansion are more aesthetically pleasing and diverse than those generated by baseline methods. Overall, this paper presents a novel and effective approach to improving the text-to-image generation experience.