Strange Attractions

Strange Attractions are imagined creatures living in the latent space of the neural network StyleGAN. Instead of using it to generate photorealistic human faces, we challenge the algorithm and explore the area outside of its intended use. Strange Attractions rise from the neural network's interrupted face generation process and reveal the network's attempt to recall a human face. There comes an absolute bewilderedness from these neural encounters' erratic beauty, vivid colors, and stunning composition. The hallucinated meta faces are carrying the strangest emotions. From quirky looks to abstract ghosts, Strange Attractions present a wide range of visual possibilities behind the process of image synthesis, while stressing the importance of freedom in experimentation with open, generative ML/AI models.

Project by Lenka Hamosova and Pavol Rusnak

Imagined by StyleGAN (Karras et al.)

Augmented Reality: Instagram Filter / Snapchat Lens

Shop: Strange Attractions Prints / Pexeso Memo Game

Exhibited at DOX Centre for Contemporary Art and NeurIPS 2020 Workshop

Click on a face to get a new one …