Recent text-conditioned image generation models have demonstrated an exceptional capacity to produce diverse and creative imagery with high visual quality. However, when pre-trained on billion-sized datasets randomly collected from the Internet, where potential biased human preferences exist, these models tend to produce images with common and recurring stereotypes, particularly for certain racial groups. In this paper, we conduct an initial analysis of the publicly available Stable Diffusion model and its derivatives, highlighting the presence of racial stereotypes. These models often generate distorted or biased images for certain racial groups, emphasizing stereotypical characteristics. To address these issues, we propose a framework called "RS-Corrector", designed to establish an anti-stereotypical preference in the latent space and update the latent code for refined generated results. The correction process occurs during the inference stage without requiring fine-tuning of the original model. Extensive empirical evaluations demonstrate that the introduced \themodel effectively corrects the racial stereotypes of the well-trained Stable Diffusion model while leaving the original model unchanged.

翻译：近期，基于文本条件的图像生成模型展现了生成多样且富有创意的高视觉质量图像的卓越能力。然而，当这些模型在从互联网随机收集的数十亿级数据集上预训练时，由于其中可能存在带有偏见的潜在人类偏好，它们倾向于生成带有常见且重复的刻板印象的图像，特别是针对某些种族群体。在本文中，我们对公开的Stable Diffusion模型及其衍生模型进行了初步分析，揭示了其中存在的种族刻板印象。这些模型往往会为特定的种族群体生成扭曲或有偏见的图像，并强调其刻板特征。为解决这些问题，我们提出了一种名为“RS-Corrector”的框架，旨在潜在空间中建立反刻板印象偏好，并通过更新潜在代码来优化生成结果。该校正过程发生在推理阶段，无需对原始模型进行微调。大量实证评估表明，所提出的模型能有效纠正训练良好的Stable Diffusion模型中的种族刻板印象，同时保持原始模型不变。