Training a Heavy Metal Artwork Generator using StyleGAN2-ADA

Introduction

Generative adversarial networks (GANs) are a particular kind of machine learning models that are designed to learn a distribution of data from a representative sample. After training, you can sample from the distribution, generating novel examples that were not present in the original training set. So, for example, you can “show” a GAN a bunch of images of faces and then the GAN will be able to generate new faces. This is exactly what’s behind the curtains in the famous “this person does not exist” website.

GANs have seen a lot of improvement in the last few years since their invention in 2014. In particular, one of the leading research groups in GANs is Tero Karra’s group at NVIDIA, who have managed to stay at the top of the state of the art with a series of ground breaking publications:

In their latest work, they describe StyleGAN2-ADA, a new version of StyleGAN that is particularly notable because it keeps the high quality results from previous works, but at the same time, it significantly reduces the amount of required training images. It is also more compute efficient than its predecessors. This improvements make it possible to train high quality output GANs a lot more feasible. Now, instead of having to build or obtain a dataset of tens of thousands of images, it is possible to obtain decent results with just a few thousands of images or even less. Take a look at these results that the NVIDIA team got using transfer learning from FFHQ on a very small dataset with only 1336 images scraped from the MET’s website:

Generated images by training StyleGAN2-ADA on the METFACES dataset, originally published in the StyleGAN2-ADA paper.

But, what does heavy metal have to do with all of this? Well, the truth is that, besides my passion for machine learning, I have a parallel life in which I am a symphonic power metal guitarist. Metal albums artwork are some of the finest pieces of art out there (or at least that’s what we metal fans think!), and so I thought it would be a great way to test StyleGAN2-ADA with metal albums front covers, and see if we could get an unlimited source of these great and inspiring images.

The cover artwork of Crystal Gates (that’s our band 😇) first studio release “A Quest For Life”, crafted by the French artist JP Fournier. Isn’t it beautiful?

A heavy metal artwork dataset

I managed to gather a total of 16.176 heavy metal album covers from 5.882 different artists. Here’s a sample:

A sample of the cover artworks gathered in the dataset.

To build the dataset, I followed these steps:

  • I obtained a list of artist and album names from DarkLyrics.com using metalparser, a pretty cool and easy to use python package to get data from Dark Lyrics.

Thanks to these resources, building the dataset ended up being much easier than I expected. It is available as a Kaggle dataset here. It’s a first version and there’s lots of ways to improve it to make it usable for other purposes (an artwork to subgenre classifier maybe?), so expect it to be updated soon.

Training the heavy metal artwork GAN

To train the model, I used Google Colab, a Jupyter notebook environment by Google that provides free GPU compute access, and also integrates very well with Google Drive. In particular I used this training script by Derrick Schultz, which is pretty simple to follow along and takes care of some stuff like the Google Drive integration and the ability to resume training if something fails or Colab disconnects your environment (which actually happens after a certain amount of hours).

Like in many other cases, the script uses transfer learning from a previous trained model, in order to save time and compute. Transfer learning is a technique that aims to reduce training time by using a previously trained version of your model in a somewhat similar dataset. Instead of starting from scratch, you resume training starting from the pretrained model. This is particularly helpful with bigger models that take weeks to train in expensive infrastructure. In this case, I selected the FFHQ faces model, at 512 pixels resolution. It may seem weird to have a faces generator as a starting point, but it actually works.

Results

The first results after just a few minutes of training were pretty scary. A disturbing set of faces somewhat transfigured into album artwork. That may not be that bad if you are looking for some psychedelic horror image for your progressive death metal project:

A sample set of fake images generated during the first stages of training the model.

After eight hours of training, things started looking a bit more reasonable, but still quite abstract:

A sample set of fake images generated after eight hours of training the model.

After two days, it looks better and characters start to appear more clearly, but it will probably take much longer and some experimentation with hyper parameters before getting images that actually make sense:

A sample set of fake images generated after two days of training the model.

Artwork generation

I created a small Colab notebook to easily run the model and generate new artwork. You can check it out here. There, you will be able to generate album covers using random numbers as “seeds”.

This is an example using 666 as seed 😈:

Next steps

Obvious next steps for this work include training this model further, to see if it starts generating less abstract art, and also training other models with subsets for specific sub genres. A power metal artwork generator would be awesome!

Also, a great improvement for these models would be to gain the ability either to specify the artist name and album title and have the model generate the image conditioned on it; or even better, to be able to somehow mask the logos and titles in the training dataset, in order to generate only the artwork and then be able to place the logo and title manually.

Conclusions

In this article we went through a small case study of how to create a relatively small dataset and train an image generator with it, using NVIDIA’s StyleGAN2-ADA. Along with many others, this proves NVIDIA’s point that it is actually possible to generate high quality images with their model, using a limited number of training examples. In particular, using transfer learning from previous pretrained models, with freely available resources, and even when the target domain is quite different from the starting model.

Let me know your thoughts and suggestions. It would also be great to see if you generate some cool artwork with this or with your own model using this dataset. Please share it!

You can also follow me on Twitter at @benjaminmachin, reach out on Linkedin or directly email me.

Machine Learning Engineer