Derivative-Works is an experiment in using machine learning to create image collages.
source code for https://derivative.works
Derivative-Works is an experiment in using machine learning to create image collages.
The algorithm cuts out shapes from images and rearranges them to create a face.
All of the reference images are in the public domain, created in Artbreeder using BigGAN and StyleGAN.
The primary difference between this method and vanilla inversion is the input medium: instead of optimizing pixels directly, we optimize parameters. This simple technique lead to a variety of textures and compositions and the videos show the actual optimizations.
The website listed above. Uses svelte + typescript + sapper + tailwind
See make_collage.ipynb to make your own
Exporting the data for the site is a little buggy 😇