Portrait transformed and generated by a multi-step GAN process using a custom trained pix2pix model that was trained on scanning electron microscopy imagery.
I am applying deep learning techniques in an attempt to discover new forms of aesthetics and blur the lines between human and machine creativity. I have been using image focussed neural network architectures since the release of Deep Dream (I was part of the Grey Area deep dream art show), ppgn, style transfer, pix2pix and CycleGAN are architectures I have investigated and experimented with in an artistic context. I’ve shown several of my “Neurographer” works at Ars Electronica 2017.
Images and Videos Courtesy of Mario Klingemann