Paper ID: 2310.04816

Hacking Generative Models with Differentiable Network Bending

Giacomo Aldegheri, Alina Rogalska, Ahmed Youssef, Eugenia Iofinova

In this work, we propose a method to 'hack' generative models, pushing their outputs away from the original training distribution towards a new objective. We inject a small-scale trainable module between the intermediate layers of the model and train it for a low number of iterations, keeping the rest of the network frozen. The resulting output images display an uncanny quality, given by the tension between the original and new objectives that can be exploited for artistic purposes.

Submitted: Oct 7, 2023