> 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](/model-coverage/release-log) for recipe-backed checkpoints of every model type.

| Date       | Model                                                                                                     | Architectures                         | Recipe                                                                                                                  |
| :--------- | :-------------------------------------------------------------------------------------------------------- | :------------------------------------ | :---------------------------------------------------------------------------------------------------------------------- |
| 2026-08-04 | [LTX-2.3](/model-coverage/diffusion/lightricks/ltx-2-3) (documentation)                                   | Dual-stream DiT (Flow Matching)       |                                                                                                                         |
| 2026-07-28 | [LTX-2.3-Diffusers](/model-coverage/diffusion/diffusers/ltx-2-3)                                          | Diffusion Transformer (Flow Matching) | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/ltx2_3_t2v_flow.yaml)           |
| 2026-07-27 | [Qwen-Image-Edit-2511](/model-coverage/diffusion/qwen/qwen-image)                                         | Diffusion Transformer (Flow Matching) | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/qwen_image_edit_2511_flow.yaml) |
| 2026-06-09 | [FLUX.2-dev](/model-coverage/diffusion/black-forest-labs/flux-2-dev)                                      | Diffusion Transformer (Flow Matching) | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/flux2_t2i_flow.yaml)            |
| 2026-06-08 | [Wan2.2-T2V-A14B-Diffusers](/model-coverage/diffusion/wan-ai/wan-2-2-t2v-a14b)                            | DiT (Flow Matching), two-stage        | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/wan2_2_t2v_flow.yaml)           |
| 2026-06-05 | [Wan2.1-T2V-14B-Diffusers](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B-Diffusers)                        |                                       | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/wan2_1_t2v_flow.yaml)           |
| 2026-04-20 | [Qwen-Image](/model-coverage/diffusion/qwen/qwen-image)                                                   | Diffusion Transformer (Flow Matching) | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/qwen_image_t2i_flow.yaml)       |
| 2026-03-03 | [Wan2.1-T2V-1.3B-Diffusers](/model-coverage/diffusion/wan-ai/wan-2-1-t2v)                                 | DiT (Flow Matching)                   | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/wan2_1_t2v_flow_multinode.yaml) |
| 2026-03-03 | [HunyuanVideo-1.5-Diffusers-720p\_t2v](/model-coverage/diffusion/hunyuanvideo-community/hunyuanvideo-1-5) | DiT (Flow Matching)                   | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/hunyuan_t2v_flow.yaml)          |
| 2026-03-03 | [FLUX.1-dev](/model-coverage/diffusion/black-forest-labs/flux-1-dev)                                      | DiT (Flow Matching)                   | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/diffusion/finetune/flux_t2i_flow.yaml)             |

## 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](/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](/recipes-e2e-examples/diffusion-fine-tuning).