Defining and Quantifying Creative Behavior in Popular Image Generators

TL;DR

This paper introduces quantitative measures to evaluate the creativity of popular image-generating AI models, aligning with human intuition and aiding users in selecting suitable models for specific tasks.

Contribution

It proposes new practical metrics for assessing AI creativity and validates them on popular image-to-image models, bridging the gap between subjective perception and quantitative evaluation.

Findings

Measures conform to human intuition

Effective in comparing different models

Assists users in model selection

Abstract

Creativity of generative AI models has been a subject of scientific debate in the last years, without a conclusive answer. In this paper, we study creativity from a practical perspective and introduce quantitative measures that help the user to choose a suitable AI model for a given task. We evaluated our measures on a number of popular image-to-image generation models, and the results of this suggest that our measures conform to human intuition.