Physics-inspired Generative AI models via real hardware-based noisy quantum diffusion

TL;DR

This paper introduces two physics-inspired quantum diffusion protocols that leverage quantum properties and hardware noise to enhance generative AI models, demonstrating improved image generation quality.

Contribution

It proposes and implements two novel quantum diffusion protocols inspired by physics, utilizing quantum stochastic walks and hardware noise to improve generative AI performance.

Findings

Quantum stochastic walks produce more robust MNIST images with lower FID.

Using real IBM quantum hardware, noise is exploited to generate images.

The methods show potential for scalable quantum generative AI.

Abstract

Quantum Diffusion Models (QDMs) are an emerging paradigm in Generative AI that aims to use quantum properties to improve the performances of their classical counterparts. However, existing algorithms are not easily scalable due to the limitations of near-term quantum devices. Following our previous work on QDMs, here we propose and implement two physics-inspired protocols. In the first, we use the formalism of quantum stochastic walks, showing that a specific interplay of quantum and classical dynamics in the forward process produces statistically more robust models generating sets of MNIST images with lower Fr\'echet Inception Distance (FID) than using totally classical dynamics. In the second approach, we realize an algorithm to generate images by exploiting the intrinsic noise of real IBM quantum hardware with only four qubits. Our work could be a starting point to pave the way for new scenarios for large-scale algorithms in quantum Generative AI, where quantum noise is neither mitigated nor corrected, but instead exploited as a useful resource.