Album cover art image generation with Generative Adversarial Networks

TL;DR

This paper explores the artistic potential of GANs, specifically StyleGAN2, in generating and customizing album cover art by training on a large dataset and manipulating styles.

Contribution

It demonstrates the application of state-of-the-art GANs to generate and tailor album cover art, extending GAN use beyond traditional photo-realistic image synthesis.

Findings

StyleGAN2 can generate album covers with diverse styles.

Training on 80K album covers is feasible and effective.

Style mixing allows genre-specific customization.

Abstract

Generative Adversarial Networks (GANs) were introduced by Goodfellow in 2014, and since then have become popular for constructing generative artificial intelligence models. However, the drawbacks of such networks are numerous, like their longer training times, their sensitivity to hyperparameter tuning, several types of loss and optimization functions and other difficulties like mode collapse. Current applications of GANs include generating photo-realistic human faces, animals and objects. However, I wanted to explore the artistic ability of GANs in more detail, by using existing models and learning from them. This dissertation covers the basics of neural networks and works its way up to the particular aspects of GANs, together with experimentation and modification of existing available models, from least complex to most. The intention is to see if state of the art GANs (specifically StyleGAN2) can generate album art covers and if it is possible to tailor them by genre. This was attempted by first familiarizing myself with 3 existing GANs architectures, including the state of the art StyleGAN2. The StyleGAN2 code was used to train a model with a dataset containing 80K album cover images, then used to style images by picking curated images and mixing their styles.