Metadata-Version: 2.1
Name: wyn-wav2lip
Version: 0.2.2
Summary: A simple package to run Wav2Lip for lip synchronization with quality enhancements.
Author: Your Name
Author-email: your.email@example.com
Requires-Python: >=3.8,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: basicsr (==1.4.2)
Requires-Dist: batch_face (>=1.0.4,<2.0.0)
Requires-Dist: configparser (>=5.3.0,<6.0.0)
Requires-Dist: gfpgan (>=1.3.8,<2.0.0)
Requires-Dist: torch (>=2.0,<3.0)
Description-Content-Type: text/markdown

# Wav2Lip Package

Wav2Lip is a Python package that simplifies the setup and execution of the [Wav2Lip](https://github.com/anothermartz/Easy-Wav2Lip) model, a deep learning tool for lip synchronization with enhanced quality options.

```
wav2lip_project/
├── wav2lip/
│   ├── __init__.py
│   └── wav2lip.py  # Refactored class-based script with the correct name
├── pyproject.toml  # Poetry configuration file
├── README.md  # Project description and usage instructions
├── LICENSE  # License file (e.g., MIT License)
├── tests/
│   └── test_wav2lip.py  # Unit tests for the package
├── dist/  # Will contain build files after 'poetry build'
├── .gitignore  # Files to ignore in version control (optional)
└── setup.cfg  # Optional: You can include a setup.cfg for backward compatibility
```

## Features

 setup for Google Colab environments.
- Supports multiple quality settings (Fast, Improved, Enhanced).
- Integrated with GFPGAN for face upscaling.
- Easy configuration through INI files for customizable options.

## Installation

To install the Wav2Lip package, you can use [Poetry](https://python-poetry.org/) to manage dependencies.

```bash
pip install wav2lip
```

## Usage

Here's an example of how to use the `Wav2Lip` package:

```python
from wyn_wav2lip.wav2lip import *

# Initialize Wav2Lip
wav2lip = Wav2Lip()

# Setup environment (ensure that you have GPU enabled)
wav2lip.setup()

# Run: requires 2 input args: 
# - an image
# - a voice file
wav2lip.run(video_file="/content/yiqiao3.jpg", vocal_file="/content/Easy-Wav2Lip/output.mp3")
```

### Options

You can specify different options for the model, such as:

- **Quality**: `"Fast"`, `"Improved"`, or `"Enhanced"`.
- **Output Height**: `"half resolution"`, `"full resolution"`, or `"480"`.
- **Padding and Mask**: Customize mouth tracking, padding, and mask settings.

## Contributing

Feel free to open issues or contribute by submitting pull requests.

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
```

