---
title: NV-Generate Synthetic Medical Imaging
emoji: 🧠
colorFrom: green
colorTo: indigo
sdk: gradio
sdk_version: "6.14.0"
app_file: app.py
python_version: "3.11"
pinned: true
license: other
license_name: nvidia-open-model-license
license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
short_description: Synthetic 3D CT and MR generation with NVIDIA NV-Generate.
---

# NV-Generate · Synthetic Medical Imaging

A unified Hugging Face Spaces demo for NVIDIA Medtech's three open-weight 3D
medical image generators, all built on the MAISI-v2 rectified-flow architecture
(~30 inference steps each).

| Model | Modality | Output | Weights |
|---|---|---|---|
| **NV-Generate · CT** | Computed Tomography | Image + paired 132-class anatomy mask | [nvidia/NV-Generate-CT](https://huggingface.co/nvidia/NV-Generate-CT) |
| **NV-Generate · MR** | MR (multi-contrast, multi-anatomy) | Image only | [nvidia/NV-Generate-MR](https://huggingface.co/nvidia/NV-Generate-MR) |
| **NV-Generate · MR Brain** | Brain MR (T1 / T2 / FLAIR / SWI) | Image only | [nvidia/NV-Generate-MR-Brain](https://huggingface.co/nvidia/NV-Generate-MR-Brain) |

## Features

- Hero card landing → per-model workspace.
- niivue WebGL multiplanar viewer (axial / coronal / sagittal + 3D render).
- Paired 132-class anatomy mask overlay for CT (with deterministic per-label colormap + named legend).
- Window/Level presets (Soft Tissue / Lung / Bone / Brain) on the CT viewer.
- Direct NIfTI download of every generated volume + mask.
- ZeroGPU support for HF Spaces (`@spaces.GPU` decorator).

## Local development

```bash
pip install -r requirements.txt
pip install -r repos/NV-Generate-CTMR/requirements.txt
python app.py                           # http://localhost:7860
```

`app.py` auto-clones the upstream `NV-Generate-CTMR` inference repo into
`./repos/` on first run (no separate `pre-build.sh` needed). Weights are
downloaded lazily from the Hugging Face Hub the first time each model is
exercised, then cached.

## Hugging Face Spaces deployment

Recommended hardware: **ZeroGPU** (A10G or H100), since each model needs ~16–80 GB
VRAM depending on volume size.

1. Create a new Space on huggingface.co with `sdk: gradio` (already set in this
   README's frontmatter).
2. Push this repository:
   ```bash
   git remote add space https://huggingface.co/spaces/<your-username>/nv-generate
   git push space main
   ```
3. In the Space's **Settings → Hardware**, select **ZeroGPU**.
4. First build will install dependencies + clone the upstream repo. First
   generation on each model downloads weights into a persistent cache.

## License

| Component | License |
|---|---|
| This repo (Gradio glue) | Apache 2.0 |
| Upstream `NV-Generate-CTMR` source | Apache 2.0 |
| `NV-Generate-CT` weights | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) |
| `NV-Generate-MR` weights | [**NVIDIA OneWay Non-Commercial License**](https://developer.download.nvidia.com/licenses/NVIDIA-OneWay-Noncommercial-License-22Mar2022.pdf) — academic / research use only |
| `NV-Generate-MR-Brain` weights | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) |

**Not for clinical diagnostics.** This is a research demo for synthetic data
generation only.

## Credits

Built on the MAISI framework:

- **MAISI-v1** — [WACV 2025 paper](https://arxiv.org/abs/2409.11169)
- **MAISI-v2** — [AAAI 2026 paper](https://arxiv.org/abs/2508.05772)

NVIDIA Medtech, University of Zurich, Istanbul Medipol, Forithmus.
</content>
</invoke>