diontimmer / Sample-Diffusion-ComfyUI-Extension

Generate audio using ComfyUI and dance diffusion models.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Sample Diffusion ComfyUI extension

Features

Allows the use of trained dance diffusion/sample generator models in ComfyUI.
Also included are two optional extensions of the extension (lol); Wave Generator for creating primitive waves aswell as a wrapper for the Pedalboard library.
The pedalboard wrapper allows us to wrap most vst3s and control them, for now only a wrapper for OTT is included. Any suggestions are welcome.
Includes a couple helper functions.

Installation

  1. Install ComfyUI
  2. Clone/download as zip and place SampleDiffusion folder in ComfyUI/custom_nodes.
  3. Move/copy playAudio.js from SampleDiffusion to ComfyUI/web/extensions
  4. Place models in ComfyUI/models/audio_diffusion ('model_folder' entry in config.yaml is accepted).
    4.5 (Optional) Install xfer OTT VST3
  5. Launch!

Example

(Tip: right-click a node to convert an input to a pin you can connect to!)

App Screenshot

Feel free to check out my other nodes.

Acknowledgements

About

Generate audio using ComfyUI and dance diffusion models.


Languages

Language:Python 95.0%Language:JavaScript 5.0%