DigiDoppel is a JavaScript application that leverages TensorFlow to create a live avatar of your face. By utilizing face mesh technology, DigiDoppel allows you to generate a dynamic and interactive digital avatar in real-time.
- Live Face Mesh: Uses TensorFlow's face mesh technology to track facial features and movements in real time.
- Real-Time Interaction: Your avatar updates in real-time as you move and change expressions.
- Local or Web Server Support: Can be hosted on a local server or deployed on the web for easy access.
To run DigiDoppel, you'll need the following:
- A local or web server (e.g., Node.js, XAMPP, or any other HTTP server)
- A web browser that supports WebGL
- Internet connection (for TensorFlow.js and Three.js dependencies)
To run DigiDoppel, you must have a local or web server. Here’s how to set up a local server using a few common methods:
- Install Node.js.
- Navigate to the project directory in your terminal.
- Run the following command to install a simple HTTP server:
npm install -g http-server
- Start the server:
http-server
- Open your web browser and go to
http://localhost:8080
(or the port number provided).
- Install XAMPP.
- Place the DigiDoppel project folder inside the
htdocs
directory of your XAMPP installation. - Start the Apache module in XAMPP.
- Open your web browser and go to
http://localhost/DigiDoppel
.
- Once the server is running, open the project URL in your web browser.
- Allow the browser to access your webcam when prompted.
- The application will use TensorFlow.js to track your face and Three.js to generate a live 3D avatar.
- The app will start capturing your facial features in real time.
- Your live avatar will reflect your facial movements, providing an interactive 3D model of your face.
DigiDoppel relies on the following libraries:
- TensorFlow.js: For face mesh tracking
- Three.js: For rendering the 3D model
- WebGL: Ensure your browser supports WebGL for 3D rendering.
Contributions are welcome! If you'd like to contribute to DigiDoppel, please fork the repository and submit a pull request with your changes.
This project is licensed under the MIT License. See the LICENSE
file for more details.
If you encounter any issues or have questions, please contact the project maintainers or refer to the documentation provided in the project files.