> This page is for version 0.7.0 · 26.10.
> For other versions, use one of these documentation indexes:
> - Nightly (default): https://docs.nvidia.com/nemo/automodel/nightly/llms.txt
> - Latest: https://docs.nvidia.com/nemo/automodel/latest/llms.txt
> - 0.7.0 · 26.10: https://docs.nvidia.com/nemo/automodel/v0.7/llms.txt
> - 0.5.0 · 26.06: https://docs.nvidia.com/nemo/automodel/v0.5/llms.txt
> - 0.4.0 · 26.04: https://docs.nvidia.com/nemo/automodel/v0.4/llms.txt

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

# Diffusion Models

## Introduction

Diffusion models are a class of generative models that learn to produce images or videos by iteratively denoising samples from a noise distribution. NeMo AutoModel supports training diffusion models using **flow matching**, a framework that regresses velocity fields along straight interpolation paths between noise and data.

NeMo AutoModel integrates with [Hugging Face Diffusers](https://huggingface.co/docs/diffusers) for model loading and generation while providing its own distributed training infrastructure using `TrainDiffusionRecipe`. This recipe handles FSDP2 parallelization, flow matching loss computation, multiresolution bucketed data loading, and checkpoint management.

## Supported Models

This table combines recipe-backed checkpoints with documented model families. Dates show when the current checkpoint first appeared in a recipe, or when a documentation-only family page was added. See the [combined model support log](/nemo/automodel/v0.7/model-coverage/release-log) for recipe-backed checkpoints of every model type.

## Supported Workflows

* **Pretraining**: Train from randomly initialized weights on large-scale datasets
* **Fine-tuning**: Adapt pretrained model weights to a specific dataset or style
* **Generation**: Run inference with pretrained or fine-tuned checkpoints

## Dataset

Diffusion training requires pre-encoded `.meta` files containing VAE latents and text embeddings. Raw videos or images must be preprocessed before training. See the [Diffusion Dataset Preparation](/nemo/automodel/v0.7/datasets/diffusion-dataset) guide.

## Train Diffusion Models

For a complete walkthrough of training configuration, model-specific settings, and launch commands, see the [Diffusion Training and Fine-Tuning Guide](/nemo/automodel/v0.7/recipes-e2e-examples/diffusion-fine-tuning).