Inference Time Debiasing Concepts in Diffusion ModelsLucas S. Kupssinsk\"u, Marco N. Bochernitsan, Jordan Kopper, Ot\'avio Parraga, Rodrigo C. Barroshttps://arxiv.org/abs/2508.14933
Inference Time Debiasing Concepts in Diffusion ModelsWe propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models that changes the inference procedure, does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based image generation model. DeCoDi changes the diffusion process to avoid latent dimension regions of biased concepts. While most deep learning debiasing methods require complex or compute-intensive interventions, our method is designed to change only the inferen…