Explaining synthetic face images generated by diffusion models
Victor Sanchez · 2025
In this talk, I will introduce a state-of-the-art approach designed to explain face images generated by diffusion models. Specifically, I will introduce the Explainable DIffusion PRobabilistic (EDIPR) model, which is based on a classification framework. EDIPR consists of three stages: an initial clustering stage, which serves as the pre-processing step to discover groups of similar face images in the training set; a synthesizing stage, carried out by a diffusion model; and an explaining stage, which allows determining which training images contributed the most to the generation of a new face image. To provide explainability, I will also introduce two influence scores as quantitative metrics: the Normalized Influence Score (NIS) and the class-Normalized Influence Score (cNIS). These scores provide the probability that a specific training image, or class, contributes to the generation of a synthetic face image. Based on synthetic images generated using real images of the FFHQ dataset as training data, I will show that EDIPR provides robust and plausible explanations linking the training images to the synthetic images at three levels of granularity: the region, the image, and the class level.