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. Multi-Modal-CelebA-HQ can be used to train and evaluate algorithms of text-to-image-generation, text-guided image manipulation, sketch-to-image generation, and GANs for face generation and editing.
27 PAPERS • 3 BENCHMARKS