Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

Patrick Schramowski, Manuel Brack, Björn Deiseroth, Kristian Kersting; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 22522-22531

Abstract


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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schramowski_2023_CVPR, author = {Schramowski, Patrick and Brack, Manuel and Deiseroth, Bj\"orn and Kersting, Kristian}, title = {Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22522-22531} }