Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models
It addresses bias issues in generative models for researchers and practitioners, though it is incremental as it extends existing evaluation methods.
The paper analyzed text-to-image generative models by assessing image quality and social biases, finding that larger models produce higher-quality images but also exhibit inherent gender and social biases.
Advances in generative models have led to significant interest in image synthesis, demonstrating the ability to generate high-quality images for a diverse range of text prompts. Despite this progress, most studies ignore the presence of bias. In this paper, we examine several text-to-image models not only by qualitatively assessing their performance in generating accurate images of human faces, groups, and specified numbers of objects but also by presenting a social bias analysis. As expected, models with larger capacity generate higher-quality images. However, we also document the inherent gender or social biases these models possess, offering a more complete understanding of their impact and limitations.