The DiffSynFace is a large-scale synthetic face dataset, consists of 40k+ hyper-realistic synthetic face images. It leverages seven state-of-the-art diffusion-based text-to-image models (Stable Diffus
Part 3 of the synthetic facial data rendered from female fbx models. The total dataset contains around 13k facial images generated from 12 identity and the corresponding raw facial depth and head pose
