The Hidden Cost of an Image: Quantifying the Energy Consumption of AI Image Generation

TL;DR

This study empirically evaluates the energy consumption of 17 AI image generation models, revealing significant variability and trade-offs between energy use and image quality, with implications for sustainable AI practices.

Contribution

It provides a comprehensive empirical analysis of energy consumption across multiple AI image generation models, considering factors like model type, resolution, and quantization.

Findings

Energy consumption varies up to 46x among models.

Model type influences energy efficiency, with U-Net models being more efficient.

Increasing resolution raises energy use inconsistently, from 1.3x to 4.7x.

Abstract

With the growing adoption of AI image generation, in conjunction with the ever-increasing environmental resources demanded by AI, we are urged to answer a fundamental question: What is the environmental impact hidden behind each image we generate? In this research, we present a comprehensive empirical experiment designed to assess the energy consumption of AI image generation. Our experiment compares 17 state-of-the-art image generation models by considering multiple factors that could affect their energy consumption, such as model quantization, image resolution, and prompt length. Additionally, we consider established image quality metrics to study potential trade-offs between energy consumption and generated image quality. Results show that image generation models vary drastically in terms of the energy they consume, with up to a 46x difference. Image resolution affects energy consumption inconsistently, ranging from a 1.3x to 4.7x increase when doubling resolution. U-Net-based models tend to consume less than Transformer-based one. Model quantization instead results to deteriorate the energy efficiency of most models, while prompt length and content have no statistically significant impact. Improving image quality does not always come at the cost of a higher energy consumption, with some of the models producing the highest quality images also being among the most energy efficient ones.