DanceGen is an innovative application that generates dance movements based on user-provided music names. It leverages the YouTube Data API to retrieve audio files and uses the EDGE (Editable Dance Generation) machine learning model to create corresponding dance movements.
Check out our demo video to see DanceGen in action:
I have stopped the GPU VM I rented, and now only the dance animations generated in August during the launch are available. Generated dances
- Generate dance movements from any music name
- 3D visualization of generated dance movements using Autodesk FBX
- Efficient task queuing with Redis
- Secure deployment on Microsoft Azure
- File storage on Amazon S3
- User data management with MongoDB
- Backend: FastAPI, Docker
- Frontend: Next.js, TypeScript, Tailwind CSS
- Database: MongoDB
- Cache and Queue: Redis
- Cloud Services: Microsoft Azure, Amazon S3
- APIs: YouTube Data API
- 3D Visualization: Autodesk FBX
- Clone the repository:
git clone https://github.com/youngccame1/bile-ai-3d.git cd dancegen - Set up the frontend:
cd frontend npm install npm run dev
- Navigate to the application in your web browser.
- Enter the name of a song or music piece.
- Click "Generate Dance" to create a dance sequence.
- View the 3D visualization of the generated dance movements.
As of August 2024, DanceGen has gained 300 users within the first 3 days of launch.
We welcome contributions to DanceGen! Please read our Contributing Guidelines for details on our code of conduct and the process for submitting pull requests.
This project is licensed under the MIT License - see the LICENSE file for details.
- EDGE (Editable Dance Generation) model creators
- YouTube Data API
- Autodesk FBX SDK
For any queries, please reach out to your_email@example.com.