Riffusion Release v0.3 – Stable Diffusion for audio

53 points by haykmartiros 2 years ago | 5 comments
  • haykmartiros 2 years ago
    We were blown away by the community interest in our Riffusion experiment (see https://www.riffusion.com/about).

    We're now catching up and did a full rewrite to go from a hack to a quality software project. It also includes an extensible CLI tool and an interactive streamlit app for common tasks, MPS backend support, stereo spectrogram encoding, a test suite run by CI, and more. These tools provide a solid foundation to build upon.

    • ronsor 2 years ago
      Is it a good idea to save spectrograms as JPEGs? Won't the lossy compression be an issue?
      • klysm 2 years ago
        I guess you could listen to what different lossy image compression algorithms sound like
      • Stevvo 2 years ago
        Love it!
      • rafaelero 2 years ago
        Why haven't you guys used <title> <artist> <album> <lyrics> as input to generate the song? It would be much cooler.