TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation

TL;DR

This paper introduces TIAM, a new metric for evaluating how well text-to-image models generate images that match prompt content, considering object types, counts, colors, and seed influence.

Contribution

The paper proposes TIAM, a prompt-template-based metric that assesses alignment between prompts and generated images, addressing seed variability and content attributes.

Findings

Image quality varies with different seeds.

Prompt complexity affects generated content.

Some seeds produce consistently better images.

Abstract

The progress in the generation of synthetic images has made it crucial to assess their quality. While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images based on a prompt, to consider additional aspects such as to which extent the generated image matches the important content of the prompt. Moreover, although the generated images usually result from a random starting point, the influence of this one is generally not considered. In this article, we propose a new metric based on prompt templates to study the alignment between the content specified in the prompt and the corresponding generated images. It allows us to better characterize the alignment in terms of the type of the specified objects, their number, and their color. We conducted a study on several recent T2I models about various aspects. An additional interesting result we obtained with our approach is that image quality can vary drastically depending on the noise used as a seed for the images. We also quantify the influence of the number of concepts in the prompt, their order as well as their (color) attributes. Finally, our method allows us to identify some seeds that produce better images than others, opening novel directions of research on this understudied topic.