Add av (PyAV) for torchvision read_video support

Fix torch.load: add weights_only=False for PyTorch 2.6 compat

Fix torch.load: add weights_only=False for PyTorch 2.6 compat

Fix mmcv v2 import: move kaiming_init/constant_init to mmengine.model

Update requirements.txt

Update app.py

Update app.py

Update app.py

Use openmim instead of direct mmcv install, add omegaconf

Add app.py with Gradio interface for TARO inference

Create app.py

Create packages.txt

Patch mmcv imports for v2.x / mmengine compatibility

Fix requirements: mmcv 2.x, remove av, add mmengine

Add HF Space metadata to README.md

Upload 21 files

initial commit