NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation

TL;DR

NeuroPrompts is an adaptive framework that automatically enhances prompts for text-to-image models, leading to higher-quality images and user-controlled stylistic features, demonstrated through an interactive application and experiments with human-engineered prompts.

Contribution

This work introduces NeuroPrompts, a novel adaptive prompt enhancement framework that automatically improves prompt quality for text-to-image generation, reducing reliance on manual prompt engineering.

Findings

Enhanced prompts produce higher-quality images.

Automatic prompt improvement outperforms manual engineering.

Framework enables user control over stylistic features.

Abstract

Despite impressive recent advances in text-to-image diffusion models, obtaining high-quality images often requires prompt engineering by humans who have developed expertise in using them. In this work, we present NeuroPrompts, an adaptive framework that automatically enhances a user's prompt to improve the quality of generations produced by text-to-image models. Our framework utilizes constrained text decoding with a pre-trained language model that has been adapted to generate prompts similar to those produced by human prompt engineers. This approach enables higher-quality text-to-image generations and provides user control over stylistic features via constraint set specification. We demonstrate the utility of our framework by creating an interactive application for prompt enhancement and image generation using Stable Diffusion. Additionally, we conduct experiments utilizing a large dataset of human-engineered prompts for text-to-image generation and show that our approach automatically produces enhanced prompts that result in superior image quality. We make our code and a screencast video demo of NeuroPrompts publicly available.