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. Moreover, StudioGAN provides an unprecedented-scale benchmark for generative models. The benchmark includes results from GANs (BigGAN-Deep, StyleGAN-XL), auto-regressive models (MaskGIT, RQ-Transformer), and Diffusion models (LSGM++, CLD-SGM, ADM-G-U). StudioGAN is a self-contained library that provides 7 GAN architectures, 9 conditioning methods, 4 adversarial losses, 13 regularization modules, 6 augmentation modules, 8 evaluation metrics, and 5 evaluation backbones. Among these configurations, we formulate 30 GANs as representatives. Each modularized option is managed through a configuration system that works through a YAML file.
Features
- With StudioGAN, users can compare and debug various GANs with the unified computing environment
- StudioGAN provides a large collection of pre-trained GAN models, training logs, and evaluation results
- StudioGAN supports 5 types of acceleration methods with synchronized batch normalization for training
- StudioGAN is a self-contained library that provides 7 GAN architectures
- StudioGAN will automatically download the dataset once you execute main.py
- Analyze generated images
Project Samples
