Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

Understand

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).