Generative Models: Explore GAN and VAE Implementations

Understand the project

Practical overview

Use it when you want code examples to study or adapt for a local generative-model experiment, rather than a hosted inference service.

Learners studying generative-model implementations across several model families.
Developers seeking example code for local generative-model experiments.

Explore and compare GAN variants, including conditional, Wasserstein and least-squares GANs.
Study vanilla, conditional, denoising and adversarial VAE implementations.
Examine RBM training approaches and a Helmholtz machine using wake-sleep.

Before you choose

The repository is public and declares the Unlicense.

The repository includes implementations in both PyTorch and TensorFlow; its README lists installing both frameworks among setup steps.
Training-generated samples are described as being saved under model-specific out directories.
The README gives Conda environment setup instructions but no framework versions or per-example dependency mapping.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare the repository’s named environment and install its listed ML frameworks.

Install Miniconda.
From the repository, run conda env create.
Activate the environment with source activate generative-models.
Install TensorFlow and PyTorch using their respective installation instructions.

The named Conda environment is activated, with TensorFlow and PyTorch installed as listed dependencies.

The README does not give framework versions or specify which framework each individual example requires.
These are README setup instructions, not execution-tested steps.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 15 October 2026
Original website title: wiseodd/generative-models · Official homepage title · retained in its source language