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，通过将模型输出偏离原始训练分布并导向新目标。我们在模型中间层间注入小型可训练模块，在保持网络其余部分冻结的条件下进行少量迭代训练。由于原始目标与新目标之间的张力，最终输出图像呈现出超现实质感，这种特性可被用于艺术创作领域。