# VMAF Optimisation Pipeline

Automated video library optimization to AV1 using VMAF quality targeting.

## Features

- ✅ **Intelligent VMAF Fallback:** 94 → 93 → 92 → 90
- ✅ **15% Savings Estimation:** Finds exact VMAF needed for target savings
- ✅ **Real-time Output:** Live progress with ETA display
- ✅ **Multi-Machine Support:** Lock files prevent duplicate processing
- ✅ **Skip AV1 Files:** Won't re-encode already compressed content
- ✅ **Separate Logging:** TV/Movies and Content tracked separately
- ✅ **Thorough CRF Search:** More accurate VMAF/CRF determination
- ✅ **Windows/WSL Compatible:** Run on Windows or WSL with proper path mapping

## Quick Start

```bash
# Clone repository
git clone https://gitea.theflagroup.com/bnair/VMAFOptimiser.git /opt/Optmiser

# Process media
python3 /opt/Optmiser/optimise_media_v2.py /path/to/media tv_movies
```

## Documentation

- **AGENTS.md** - Complete technical documentation for AI agents/humans
- **SETUP.md** - Installation, configuration, and usage guide

## Requirements

- Python 3.8+
- FFmpeg with VMAF support
- ab-av1 v0.10.3+

## License

MIT License - See LICENSE file for details.

## Contributing

Contributions welcome! Please read AGENTS.md for architecture before contributing.