# hwalsuklee/tensorflow-generative-model-collections

Collection of generative models in Tensorflow

Repository: https://github.com/hwalsuklee/tensorflow-generative-model-collections
Canonical: https://ross.abutalabs.com/products/tensorflow-generative-model-collections
Language: Python
License: Apache-2.0
License Family: permissive
Topics: gan, vae, cgan, infogan, acgan, lsgan, wgan, dragan, ebgan, variational-autoencoder, began, tensorflow, mnist, fashion-mnist, wgan-gp, cvae, generative-adversarial-networks, generative-model, generative-models, improved-wgan
Last push: 2022-08-08T09:39:51+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3296, "days_push": 1486, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3918, forks 835 (observed 2026-08-28T04:08:29.672971+00:00)

## What it is
A collection of TensorFlow implementations of various generative models, including many GAN variants (GAN, WGAN, WGAN-GP, CGAN, infoGAN, ACGAN, EBGAN, BEGAN, etc.) and VAEs. It provides consistent architectures and reproducible results on MNIST and Fashion-MNIST for comparing generative model ideas.

## Use cases
- learn how GAN variants differ in their value functions
- reproduce and compare GAN results on MNIST
- find a reference implementation of WGAN-GP or infoGAN
- study VAE and CVAE implementations in TensorFlow
- get starter code for experimenting with generative adversarial networks

## When to choose
- you want clean, comparable reference implementations of many GAN/VAE variants
- you are studying or teaching generative models with small image datasets
- you need TensorFlow 1.x-era code matching original papers

## When to avoid
- you need production-ready or modern TensorFlow 2/PyTorch generative model tooling
- you want to train on large, high-resolution datasets
- you need actively maintained code with recent fixes

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, computer-vision, tutorials
- platform: python
- tags: gan, vae, tensorflow, generative-models, mnist, reference-implementations, gpu

## Member repositories
- hwalsuklee/tensorflow-generative-model-collections (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:29.672971+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 2026-08-29T18:25:01.571825+00:00, confidence not recorded.
  - readme: https://github.com/hwalsuklee/tensorflow-generative-model-collections (fetched 2026-08-28T04:08:29.672971+00:00, sha 9c6c049907c6)
- Data as of 2026-08-30T08:39:29.467469+00:00.