Dance Diffusion
Audio diffusion model by Harmonai for generating music samples.
About
Dance Diffusion by Harmonai, backed by Stability AI, is one of the first open-source audio diffusion models, applying diffusion directly to raw audio waveforms to generate short musical samples. It includes tools and Colab notebooks for training and fine-tuning a generative model on arbitrary audio samples, and it works directly in the waveform domain rather than on spectrograms. Released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Music & Audio Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Advanced (4/5)
- License
- MIT
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Latent diffusion model for text-to-audio, music, and speech generation.
Audio super-resolution model for upsampling audio to higher sample rates.
State-of-the-art music source separation model by Meta for splitting tracks.
Fast music generation model producing full songs with lyrics in seconds.
Open-source toolkit for audio, music, and speech generation research.
PyTorch library for deep learning research on audio generation including MusicGen and AudioGen.