riffusion-model-v1 / README.md
jm12138's picture
history blame
No virus
4.97 kB
license: creativeml-openrail-m
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - text-to-audio
inference: true
extra_gated_prompt: >-
  This model is open access and available to all, with a CreativeML OpenRAIL-M
  license further specifying rights and usage.

  The CreativeML OpenRAIL License specifies: 

  1. You can't use the model to deliberately produce nor share illegal or
  harmful outputs or content 

  2. Riffusion claims no rights on the outputs you generate, you are free to use
  them and are accountable for their use which must not go against the
  provisions set in the license

  3. You may re-distribute the weights and use the model commercially and/or as
  a service. If you do, please be aware you have to include the same use
  restrictions as the ones in the license and share a copy of the CreativeML
  OpenRAIL-M to all your users (please read the license entirely and carefully)

  Please read the full license carefully here:
extra_gated_heading: Please read the LICENSE to access this model

Riffusion PaddlePaddle Version

Riffusion is an app for real-time music generation with stable diffusion.

Read about it at https://www.riffusion.com/about and try it at https://www.riffusion.com/.

This repository contains the model files, including:

  • a diffusers formated library
  • a compiled checkpoint file
  • a traced unet for improved inference speed
  • a seed image library for use with riffusion-app

Riffusion v1 Model

Riffusion is a latent text-to-image diffusion model capable of generating spectrogram images given any text input. These spectrograms can be converted into audio clips.

The model was created by Seth Forsgren and Hayk Martiros as a hobby project.

You can use the Riffusion model directly, or try the Riffusion web app.

The Riffusion model was created by fine-tuning the Stable-Diffusion-v1-5 checkpoint. Read about Stable Diffusion here 🤗's Stable Diffusion blog.

Model Details

Direct Use

The model is intended for research purposes only. Possible research areas and tasks include

  • Generation of artworks, audio, and use in creative processes.
  • Applications in educational or creative tools.
  • Research on generative models.


The original Stable Diffusion v1.5 was trained on the LAION-5B dataset using the CLIP text encoder, which provided an amazing starting point with an in-depth understanding of language, including musical concepts. The team at LAION also compiled a fantastic audio dataset from many general, speech, and music sources that we recommend at LAION-AI/audio-dataset.

Fine Tuning

Check out the diffusers training examples from Hugging Face. Fine tuning requires a dataset of spectrogram images of short audio clips, with associated text describing them. Note that the CLIP encoder is able to understand and connect many words even if they never appear in the dataset. It is also possible to use a dreambooth method to get custom styles.


If you build on this work, please cite it as follows:

  author = {Forsgren, Seth* and Martiros, Hayk*},
  title = {{Riffusion - Stable diffusion for real-time music generation}},
  url = {https://riffusion.com/about},
  year = {2022}