Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,15 @@ By using this model, you are agreeing to the [terms and conditions](https://docs
|
|
| 32 |
Training and inference code are in:
|
| 33 |
[https://github.com/NVIDIA-Medtech/NV-Generate-CTMR/tree/main](https://github.com/NVIDIA-Medtech/NV-Generate-CTMR/tree/main).
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
## References:
|
| 36 |
[1] Zhao, Can, et al. "Maisi-v2: Accelerated 3d high-resolution medical image synthesis with rectified flow and region-specific contrastive loss." arXiv preprint arXiv:2508.05772 (2025).
|
| 37 |
|
|
|
|
| 32 |
Training and inference code are in:
|
| 33 |
[https://github.com/NVIDIA-Medtech/NV-Generate-CTMR/tree/main](https://github.com/NVIDIA-Medtech/NV-Generate-CTMR/tree/main).
|
| 34 |
|
| 35 |
+
## Download
|
| 36 |
+
For example, to download the VAE, you can run:
|
| 37 |
+
```
|
| 38 |
+
pip install -U huggingface_hub
|
| 39 |
+
huggingface-cli download nvidia/NV-Generate-CT \
|
| 40 |
+
models/autoencoder_v1.pt \
|
| 41 |
+
--local-dir ./models
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
## References:
|
| 45 |
[1] Zhao, Can, et al. "Maisi-v2: Accelerated 3d high-resolution medical image synthesis with rectified flow and region-specific contrastive loss." arXiv preprint arXiv:2508.05772 (2025).
|
| 46 |
|