What is pytorch-gan?

eriklindernoren/pytorch-gan — explained in plain English

Analysis updated 2026-06-24

★ 17,456PythonAudience · researcherComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((pytorch-gan))
    What it is
      GAN implementations
      Python scripts
      30+ variants
    Notable models
      CycleGAN
      Pix2Pix
      StarGAN
      Super-Resolution GAN
      Wasserstein GAN
    Use Cases
      Style transfer
      Image generation
      Super resolution
      Domain adaptation
    Stack
      Python
      PyTorch
    Status
      No longer maintained

mindmap root((pytorch-gan)) What it is GAN implementations Python scripts 30+ variants Notable models CycleGAN Pix2Pix StarGAN Super-Resolution GAN Wasserstein GAN Use Cases Style transfer Image generation Super resolution Domain adaptation Stack Python PyTorch Status No longer maintained

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Run a named GAN architecture from a research paper with a single command to see it generate images before implementing it yourself.

USE CASE 2

Compare multiple GAN variants such as Wasserstein GAN versus LSGAN side by side using the repo's reference implementations.

USE CASE 3

Use a working CycleGAN or Pix2Pix implementation as a starting point for an image style transfer or domain adaptation project.

What is it built with?

PythonPyTorch

How does it compare?

	eriklindernoren/pytorch-gan	pallets/click	transformeroptimus/superagi
Stars	17,456	17,486	17,516
Language	Python	Python	Python
Setup difficulty	moderate	easy	hard
Complexity	3/5	2/5	4/5
Audience	researcher	developer	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires PyTorch and a GPU for reasonable training speed, pip install requirements then run the per-variant Python script.

So what is it?

PyTorch-GAN is a collection of Python implementations of Generative Adversarial Networks (GANs) from research papers. A GAN is a type of machine-learning model in which two neural networks are trained together: one generates new samples (usually images) and the other tries to tell the generated samples apart from real ones, with both improving as they compete. Different GAN papers tweak the architecture or training objective to produce different effects, and this repository gathers many of those variants in one place. The table of contents in the README lists more than thirty implementations side by side, including the original GAN, Deep Convolutional GAN, Conditional GAN, InfoGAN, CycleGAN, Pix2Pix, BicycleGAN, BEGAN, DiscoGAN, DualGAN, Energy-Based GAN, Least Squares GAN, MUNIT, UNIT, StarGAN, Super-Resolution GAN, Wasserstein GAN with its gradient-penalty and divergence variants, and several others. Each entry includes the paper abstract, a link to the paper, and a runnable Python script. The author notes that model architectures do not always mirror the papers exactly, since the goal is to cover the core ideas rather than reproduce every layer configuration. Someone would use this as a reference library for studying or experimenting with GAN variants without having to reimplement each paper from scratch. Installation is by cloning the repo and pip installing requirements, each variant is run with a single python3 command from its implementation folder. The tech stack stated is Python and PyTorch. The author also notes the repository has gone stale and is no longer being actively maintained. The full README is longer than what was provided.

Copy-paste prompts

Prompt 1

I want to train the CycleGAN from pytorch-gan to convert summer landscape photos to winter. Walk me through the data format, training command, and how to run inference on a new image.

Prompt 2

Explain the difference between the Wasserstein GAN and the standard GAN in pytorch-gan. What problem does WGAN solve and what changes in the training loop?

Prompt 3

I want to use the Super-Resolution GAN from pytorch-gan to upscale low-resolution product images. Show me the training and inference commands and what dataset format it expects.

Prompt 4

Using the Pix2Pix implementation in pytorch-gan, how do I train a model to turn hand-drawn sketches into realistic images? What paired dataset format do I need?

Frequently asked questions