Exploring Latent Dimensions of Crowd-sourced Creativity

TL;DR

This paper investigates how to manipulate images generated by GANs to enhance or reduce their creativity, using a novel framework based on latent space exploration in a large AI creativity platform.

Contribution

It introduces a new method for identifying and manipulating latent dimensions associated with creativity in GAN-generated images.

Findings

Identified latent directions correlated with creativity levels.

Demonstrated effective manipulation of images to alter perceived creativity.

Provided a publicly available dataset and code for further research.

Abstract

Recently, the discovery of interpretable directions in the latent spaces of pre-trained GANs has become a popular topic. While existing works mostly consider directions for semantic image manipulations, we focus on an abstract property: creativity. Can we manipulate an image to be more or less creative? We build our work on the largest AI-based creativity platform, Artbreeder, where users can generate images using pre-trained GAN models. We explore the latent dimensions of images generated on this platform and present a novel framework for manipulating images to make them more creative. Our code and dataset are available at http://github.com/catlab-team/latentcreative.