StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation. StudioGAN aims to offer an identical playground for modern GANs so that machine learning researchers can readily compare and analyze a new idea.
This hub provides all the checkpoints we used to create the GAN benchmarks below.
Please visit our github repository (PyTorch-StudioGAN) for more details.
license: mit