Fix: move mmcv to requirements.txt, remove runtime install that caused infinite rebuild loop

Fix HunyuanFoley checkpoint path and add README metadata

Add HuggingFace Spaces metadata to README

Remove non-inference files from all three model folders

Add .gitignore and untrack MMAudio binary training examples

.

Restructure app.py: multi-model support (TARO, MMAudio, HunyuanFoley)

Show slot 0 by default; reveal extra slots on Generations slider drag

Rename 'Number of Samples' to 'Generations'

Multi-sample support, last-segment tail anchor fix, dynamic samples cap, gr.Blocks UI, duration=600

Remove share=True (redundant on HF Spaces)

Add crossfade duration/dB controls, inference caching, share=True

Support videos longer than 8.2s via overlapping inference + 2s +3dB crossfade stitching

Fix all indentation errors - consistent 4-space indentation throughout

Fix RuntimeError: pad onset_feats to truncate_onset=120 when video is shorter than 8.2s

Fix all indentation errors - consistent 4-space indentation throughout

Update app.py

Fix vocoder float32 cast error; default seed is now random

Update app.py

Fix EinopsError: handle videos with frame count not divisible by 30

Fix indentation errors in app.py

Update app.py

Strip original audio from uploaded videos before processing and final output

Update app.py

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