Skip to content
Node packVerifiedExternal
Open source

ComfyUI-MMAudio

Maintainer@kijaiCgrade

Package profile

Status
Verified
Publisher
@kijai
Source
GitHub
Stars
580

README

ComfyUI nodes to use MMAudio

WIP WIP WIP

https://github.com/user-attachments/assets/9515c0f6-cc5d-4dfe-a642-f841a1a2dba5

Installation

Clone this repo into custom_nodes folder.

Install dependencies: pip install -r requirements.txt or if you use the portable install, run this in ComfyUI_windows_portable -folder:

python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-MMAudio\requirements.txt

Models are loaded from ComfyUI/models/mmaudio

Safetensors available here:

https://huggingface.co/Kijai/MMAudio_safetensors/tree/main

Nvidia bigvganv2 (used with 44k mode)

https://huggingface.co/nvidia/bigvgan_v2_44khz_128band_512x

is autodownloaded to ComfyUI/models/mmaudio/nvidia/bigvgan_v2_44khz_128band_512x

Nodes in this pack

4 nodes
  • MMAudioFeatureUtilsLoader
  • MMAudioModelLoader
  • MMAudioSampler
  • MMAudioVoCoderLoader

Related resources

11 connections

Sources

2 sources
GitHubSourceVersion 8eaeb72edc3aaf2059b57f2d96a1f6f689f19ae2
github.com/kijai/ComfyUI-MMAudio

Verified Oct 15

GitHubSource
github.com/kijai/ComfyUI-MMAudio

Verified Oct 24

Source excerpts

1 excerpt

Source context: Repo kijai/ComfyUI-MMAudio