GAN implementations
PyTorch implementations of a wide range of GAN architectures from research papers.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
unified PyTorch GAN library with common APIs, if you prefer a structured library
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
minimal single-GAN example, choose for a tiny starting point
A very simple generative adversarial network (GAN) in PyTorch
older multi-framework collection also covering VAE, if you want TF examples
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
specific DCGAN in TensorFlow, if you only need that model
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
old TensorFlow collection, for TF users seeking the seed's model set
Collection of generative models in Tensorflow
very old PyTorch collection similar to the seed
Collection of generative models in Pytorch version.
old notebook collection of GANs in PyTorch and TF
Generative Adversarial Networks implemented in PyTorch and Tensorflow
specific DiscoGAN implementation, if you need that model alone
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
old Keras GAN collection, for Keras users
Keras Generative Adversarial Networks
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
GUI tool for interactive image generation, not a code library
Interactive Image Generation via Generative Adversarial Networks
browser-based interactive GAN visualization, not a code library
GAN Lab: An Interactive, Visual Experimentation Tool for Generative Adversarial Networks
These projects were analysed and named PyTorch-GAN among their alternatives. The relationship is not symmetric — how PyTorch-GAN rates them is a separate judgement, made when PyTorch-GAN is analysed in its own right.
calls PyTorch-GAN “choose it for a dedicated and broader set of PyTorch GAN implementations than the seed's GAN section.”
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
calls PyTorch-GAN “A collection of PyTorch GAN implementations including the seed models, but educational and less maintained.”
Image-to-Image Translation in PyTorch
calls PyTorch-GAN “use when you want a broad GAN-only set of PyTorch examples and can accept stale code.”
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.