> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/fastgen/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/fastgen/_mcp/server.

# NVIDIA FastGen Overview

> Train, distill, and evaluate diffusion models across modalities with PyTorch.

FastGen is a PyTorch library for training and distilling diffusion models into fast generative models. Use it to fine-tune a teacher, train a student that generates in fewer steps, and run inference and evaluation.

## Start here

* [Get started](/fastgen/get-started): install FastGen and run the CIFAR-10 training and inference example.
* [Run inference](/fastgen/inference): generate outputs from a teacher or student model.
* [Prepare your dataset](/fastgen/datasets): choose a loader and supply your training data.
* [Troubleshoot a run](/fastgen/troubleshooting): resolve common configuration, memory, and checkpoint issues.

## What you can do

* Distill diffusion models across modalities such as image, video, and audio into students that use fewer generation steps.
* Fine-tune a supported model on your data, including conditional and causal generation tasks.
* Run inference and evaluate teacher and student models.

## Core concepts

A [configuration](/fastgen/configuration) combines a [method](/fastgen/methods), a [network](/fastgen/networks), a [dataset](/fastgen/datasets), and training settings. Experiment configs are runnable starting points; model and data combinations have different prerequisites. Check the selected recipe before starting a large run.

## Learn more

[Resources](/fastgen/resources) collects external models, research projects, and integrations. See the [GitHub repository](https://github.com/NVlabs/FastGen), [issue tracker](https://github.com/NVlabs/FastGen/issues), and [release history](https://github.com/NVlabs/FastGen/releases) for source code, support, and released revisions.