An AI-powered system for generating K-pop music videos by intelligently combining video clips based on lyrics and music.
- Clone the repository:
git clone <your-repo-url>
cd video_clips- Create and configure your .env file:
cp .env.example .env
# Edit .env with your API keys and credentials- Build and run with Docker:
docker-compose up --buildvideo_clips/- Directory for storing 5-second video clipsmain.py- Main application entry pointsrc/- Source code directorydatabase/- Database models and operationsvideo/- Video processing utilitiesai/- AI and OpenAI integration
- Create initial music videos using your preferred video editor
- Use ffmpeg to split videos into 5-second clips:
ffmpeg -i video.mp4 -c copy -map 0 -segment_time 5 -f segment video_clips/clip_%03d.mp4- Upload clips to the video server:
# Upload script will be provided in future updates- Run tests:
docker-compose run app python -m pytest - Format code:
docker-compose run app black . - Lint code:
docker-compose run app flake8
- Push changes to GitHub
- Pull on Linode server
- Build and run Docker container:
docker-compose -f docker-compose.prod.yml up -dMIT