From paintbrush to pixel: A review of deep neural networks in AI-generated art

TL;DR

This paper reviews the evolution of deep neural networks used in AI-generated art, from early convolutional models to advanced diffusion techniques, highlighting progress, key models, and their capabilities.

Contribution

It provides a comprehensive overview of neural network architectures in AI art, comparing models like DeepDream, Stable Diffusion, and DALL-E 3, and analyzing their strengths and limitations.

Findings

Deep neural networks have rapidly advanced AI-generated art.

Models like DALL-E 3 produce highly realistic images.

Comparison highlights strengths and limitations of key models.

Abstract

This paper delves into the fascinating field of AI-generated art and explores the various deep neural network architectures and models that have been utilized to create it. From the classic convolutional networks to the cutting-edge diffusion models, we examine the key players in the field. We explain the general structures and working principles of these neural networks. Then, we showcase examples of milestones, starting with the dreamy landscapes of DeepDream and moving on to the most recent developments, including Stable Diffusion and DALL-E 3, which produce mesmerizing images. We provide a detailed comparison of these models, highlighting their strengths and limitations, and examining the remarkable progress that deep neural networks have made so far in a short period of time. With a unique blend of technical explanations and insights into the current state of AI-generated art, this paper exemplifies how art and computer science interact.