Multi-Modal CelebA-HQ

Multi-Modal-CelebA-HQ is a large-scale face image dataset that has 30,000 high-resolution face images selected from the CelebA dataset by following CelebA-HQ. Each image has high-quality segmentation mask, sketch, descriptive text, and image with transparent background.

多模态CelebA-HQ（Multi-Modal-CelebA-HQ）是一款大规模人脸图像数据集，其参照CelebA-HQ的筛选流程从CelebA数据集中遴选得到30000张高分辨率人脸图像。每张图像均附带高质量分割掩码（segmentation mask）、线条草图（sketch）、描述性文本以及透明背景图像。