Stable Diffusion with Continuous-time Neural Network

TL;DR

This paper explores the use of continuous-time cellular neural networks for image generation, demonstrating their superior performance and faster training compared to discrete-time models, with promising implications for energy efficiency.

Contribution

It introduces the application of continuous-time cellular neural networks to image generation, showing improvements over traditional discrete-time models in quality and training speed.

Findings

Higher quality images generated with cellular neural networks

Faster training times compared to discrete-time models

Potential for more energy-efficient image generation

Abstract

Stable diffusion models have ushered in a new era of advancements in image generation, currently reigning as the state-of-the-art approach, exhibiting unparalleled performance. The process of diffusion, accompanied by denoising through iterative convolutional or transformer network steps, stands at the core of their implementation. Neural networks operating in continuous time naturally embrace the concept of diffusion, this way they could enable more accurate and energy efficient implementation. Within the confines of this paper, my focus delves into an exploration and demonstration of the potential of celllular neural networks in image generation. I will demonstrate their superiority in performance, showcasing their adeptness in producing higher quality images and achieving quicker training times in comparison to their discrete-time counterparts on the commonly cited MNIST dataset.