# NEXUS-VideoModel v1.1 HQ (Stable Training)

Trained with gradient explosion protection and NaN recovery.

## Results
- Loss: 0.1117
- PSNR: 19.58 dB
- Neurons: 153

## Usage
```python
from huggingface_hub import snapshot_download
import sys

model_dir = snapshot_download("amewebstudio/nexus-videomodel-v1.1-hq")
sys.path.insert(0, model_dir)

from modeling_nexus import NexusVideoModel
model = NexusVideoModel.from_pretrained(model_dir)
video = model.generate(n_frames=16, temperature=0.3)
```