Main Purpose
Real-time music generation using stable diffusion
Key Features
- Latent text-to-image diffusion model for generating spectrogram images
- Conversion of spectrograms into audio clips
- Fine-tuning capabilities for custom styles and creative processes
- Integration with the Riffusion web app
Use Case
- Generation of artworks, audio, and use in creative processes
- Applications in educational or creative tools
- Research on generative models
