Riffusion is a free and open source real-time music and audio generation library with stable diffusion, where the user simply enters a description of the music and the AI generates music in the corresponding style. The open source project was launched by Seth Forsgren and Hayk Martiros. The principle behind Riffusion is to fine-tune spectrograms based on Stable Diffusion (a text-to image model), which is a visual representation of audio showing the amplitude of different frequencies over time, and then convert the high fidelity spectrogram image to audio. Riffu...