1 code implementation • NeurIPS 2023 • Benno Krojer, Elinor Poole-Dayan, Vikram Voleti, Christopher Pal, Siva Reddy
We also measure the stereotypical bias in diffusion models, and find that Stable Diffusion 2. 1 is, for the most part, less biased than Stable Diffusion 1. 5.
4 code implementations • ACL 2022 • Nicholas Meade, Elinor Poole-Dayan, Siva Reddy
Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on.