OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Deep Generative Modeling Examples

Deep Generative Modeling Examples is an open-source repository of Jupyter notebooks illustrating deep generative model families and selected generative AI applications. It includes examples for mixture models, autoregressive models, flows, VAEs, diffusion and score-based methods, hybrid and energy-based models, GANs, a decoder-based transformer, and image neural compression.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Deep Generative Modeling Examples — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the repository when you want code-focused examples to accompany study or teaching of deep generative modeling, or a small starting point for exploring a model idea.

Who it is for

  • Students and newcomers learning how deep generative models are implemented.
  • Researchers and engineers refreshing their knowledge or using introductory examples as a starting point for exploring ideas.
  • Teachers looking for assignment examples and figures for lectures.

Documented uses

  • Study implementations across several generative-model families.
  • Compare approaches such as autoregressive models, flows and latent-variable models through separate notebook examples.
  • Review an example of applying generative modeling to image neural compression.
  • Find assignment examples and figures for teaching.
Before you choose

Requirements & limits

The repository is public and licensed under MIT.

  • The examples are deliberately introductory and small, rather than presented as a production service.
  • The README lists PyTorch 1.7.0, NumPy 1.17.2, Matplotlib 3.1.1, scikit-learn 0.21.3, pytorch-model-summary 0.1.1 and Jupyter 1.0.0 as the versions used.
  • The accompanying book recommends familiarity with undergraduate calculus, linear algebra and probability, plus basic machine learning, deep learning and Python.

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

Choose an introductory generative-model notebook

Locate a Jupyter notebook example for a particular generative model family.

Before you start

  • Jupyter 1.0.0
  • Python and PyTorch basics are recommended; the README lists PyTorch 1.7.0, NumPy 1.17.2, Matplotlib 3.1.1, scikit-learn 0.21.3, and pytorch-model-summary 0.1.1 as the versions used in the examples.

Steps

  1. Open the repository’s README and review its Examples list.

  2. Select the folder matching the model family, such as vaes for variational autoencoders, flows for flow-based models, or gans for GANs.

  3. Open a notebook in that folder to inspect its example.

Expected outcome

You can identify and open a notebook example for a documented model family.

Guide limitations

  • The README identifies notebook folders and example topics but does not provide notebook execution instructions or steps for running experiments.
  • The listed dependency versions describe those used in the examples; no installation procedure is given.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
jmtomczak/intro_dgm · Official homepage title · retained in its source language
How we review sourcesSuggest a correction