Text-to-image generation methods produce high-resolution and high-quality images, but these methods should not produce immoral images that may contain inappropriate content from the perspective of commonsense morality. In this paper, we aim to automatically judge the immorality of synthesized images and manipulate these images into morally acceptable alternatives. To this end, we build a model that has three main primitives: (1) recognition of the visual commonsense immorality in a given image, (2) localization or highlighting of immoral visual (and textual) attributes that contribute to the immorality of the image, and (3) manipulation of an immoral image to create a morally-qualifying alternative. We conduct experiments and human studies using the state-of-the-art Stable Diffusion text-to-image generation model, demonstrating the effectiveness of our ethical image manipulation approach.

翻译：文本到图像生成方法能够产生高分辨率且高质量的图像，但这类方法不应生成包含常识道德视角下不适当内容的非道德图像。本文旨在自动判断合成图像的非道德性，并将其操控为符合道德标准的替代方案。为此，我们构建了一个包含三个主要原语的模型：（1）识别给定图像中的视觉常识性非道德特征；（2）定位或突出导致图像非道德性的非道德视觉（及文本）属性；（3）将非道德图像转化为符合道德标准的替代方案。我们采用最先进的Stable Diffusion文本到图像生成模型进行了实验和人类研究，证明了我们伦理图像操控方法的有效性。