论文标题
安全潜在扩散：在扩散模型中减轻不适当的变性
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
论文作者
论文摘要
文本条件生成模型最近在图像质量和文本对齐中取得了惊人的结果，因此被用于快速增长的应用程序。由于它们是高度数据驱动的，依靠从互联网随机刮下来的数十亿个数据集，因此，他们也表现出了退化和偏见的人类行为。反过来，他们甚至可能会加剧这种偏见。为了帮助应对这些不希望的副作用，我们提出了安全的潜扩散（SLD）。具体而言，为了衡量由于未经过滤和不平衡的训练集而导致的不当变性，我们建立了一个新型的图像生成测试床不适当的图像提示（I2P），具有专用的，现实世界中的图像到文本提示，涵盖了诸如裸露和暴力之类的概念。正如我们详尽的经验评估所表明的那样，在扩散过程中，引入的SLD删除并抑制了不适当的图像部分，无需额外的培训，也不对整体图像质量或文本对齐进行不利影响。
Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on billion-sized datasets randomly scraped from the internet, they also suffer, as we demonstrate, from degenerated and biased human behavior. In turn, they may even reinforce such biases. To help combat these undesired side effects, we present safe latent diffusion (SLD). Specifically, to measure the inappropriate degeneration due to unfiltered and imbalanced training sets, we establish a novel image generation test bed-inappropriate image prompts (I2P)-containing dedicated, real-world image-to-text prompts covering concepts such as nudity and violence. As our exhaustive empirical evaluation demonstrates, the introduced SLD removes and suppresses inappropriate image parts during the diffusion process, with no additional training required and no adverse effect on overall image quality or text alignment.
