# HyperGAN/HyperGAN

Composable GAN framework with api and user interface

Repository: https://github.com/HyperGAN/HyperGAN
Canonical: https://ross.abutalabs.com/products/hypergan
Language: Python
License: MIT
License Family: permissive
Topics: gan, unsupervised-learning, generative-adversarial-network, artificial-intelligence, machine-learning, machine-learning-api, python, online-learning, computer-vision, pytorch, sponsors, hypergan
Last push: 2023-01-21T17:54:27+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3722, "days_push": 1320, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1183, forks 160 (observed 2026-08-28T04:03:54.461310+00:00)

## What it is
HyperGAN is a composable GAN (generative adversarial network) framework built on PyTorch, offering both a Python API and a CLI with a user interface for training and sampling. It lets developers, researchers, and artists configure, train, and share GAN models via JSON configuration templates.

## Use cases
- train a GAN on my own image dataset
- generate images with a generative adversarial network
- experiment with composable GAN architectures in pytorch
- create a colorizer or image-to-image GAN model
- sample images from a trained GAN checkpoint
- learn how GANs work with a hands-on framework

## When to choose
- you want a configurable, preset-driven GAN trainer on PyTorch
- you need both a CLI and a Python API for GAN training and sampling
- you are an artist or researcher generating images without writing model code from scratch

## When to avoid
- you need state-of-the-art diffusion or transformer generative models
- you require a project under heavy active development or frequent releases
- you need non-image modalities like text or audio generation

## Facets
- artifact type: framework
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: machine-learning, deep-learning, artificial-intelligence, computer-vision, image-processing
- platform: python, windows
- tags: gan, generative-adversarial-network, pytorch, unsupervised-learning, image-generation, online-learning, linux, macos, gpu

## Member repositories
- HyperGAN/HyperGAN (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.461310+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:24:30.757675+00:00, confidence not recorded.
  - readme: https://github.com/HyperGAN/HyperGAN (fetched 2026-08-28T04:03:54.461310+00:00, sha ebc5f66edadc)
- Data as of 2026-08-30T08:39:29.467469+00:00.