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.

翻译：本文提出一种“破解”生成模型的方法，使其输出偏离原始训练分布，逼近新的目标。我们在模型的中间层之间注入一个可训练的小型模块，在保持网络其余部分冻结的情况下进行少量迭代训练。由于原始目标与新目标之间的张力，最终输出的图像呈现出一种诡谲的质感，这种特性可被用于艺术创作。