Quantum Latent Diffusion Models

TL;DR

This paper introduces a quantum latent diffusion model that integrates quantum circuits into the latent space of generative models, showing improved image quality and feature extraction over classical models, especially in limited data scenarios.

Contribution

It presents the first quantum latent diffusion model leveraging variational circuits, demonstrating advantages over classical models in image generation and few-shot learning.

Findings

Quantum models outperform classical in image quality metrics.

Quantum models excel in few-shot learning scenarios.

Quantum advantage persists with fewer training data.

Abstract

The introduction of quantum concepts is increasingly making its way into generative machine learning models. However, while there are various implementations of quantum Generative Adversarial Networks, the integration of quantum elements into diffusion models remains an open and challenging task. In this work, we propose a potential version of a quantum diffusion model that leverages the established idea of classical latent diffusion models. This involves using a traditional autoencoder to reduce images, followed by operations with variational circuits in the latent space. To effectively assess the benefits brought by quantum computing, the images generated by the quantum latent diffusion model have been compared to those generated by a classical model with a similar number of parameters, evaluated in terms of quantitative metrics. The results demonstrate an advantage in using a quantum version, as evidenced by obtaining better metrics for the images generated by the quantum version compared to those obtained by the classical version. Furthermore, quantum models continue to outperform even when considering small percentages of the dataset for training, demonstrating the quantum's ability to extract features more effectively even in a few shot learning scenario.