ComfyUI_Jags_Audiotools

★ 100

音频生成波形合成VST3封装Pedalboard集成

为ComfyUI提供音频生成与处理工具，支持dance diffusion样本、原始波形生成及Pedalboard/VST3封装，便于一体化音频工作流。

💡 在ComfyUI中生成舞蹈扩散音频样本并应用VST特效。

🍴 10 Forks💻 Python🔄 2025-03-20

🔗 GitHub 原文

📦

网盘下载

复制链接后前往夸克网盘下载

https://pan.quark.cn/s/86a6deb1b5f6

📦 requirements.txt

einops
pandas
prefigure
pytorch_lightning
scipy
torch
torchaudio
tqdm
wandb
matplotlib
torchvision
k-diffusion
PySoundFile
black
diffusers
v-diffusion-pytorch
pydub
pygame
tk
numpy
audio_diffusion_pytorch

📄 README

🎙️ComfyUI_Jags_Audiotools🎙️

A collection amazing audio tools for working with audio and sound files in comfyUI

✨🍬Please note the work in this repo is not completed and still in progress and code will break until all things are sorted. Please wait as will announce same in the update here. Thanks for your support. Also note for any issues on the nodes, kindly share your workflow and also always update comfyUI base including all dependencies.✨🍬

“As on date some three nodes are having issues which is being resolved , especially load audio and play audio nodes”

we are also adding functionality for LSP plugins and Open-Source Audio Plugins & Apps; if you have some cool suggestions would welcome creating a issue on same so can work on it to add same in.

🌈 🍬 Note we have made changes to the original repo by Diontimmer here and thankful to him for making this possible , adding new nodes to experiment and certain features, experimental audio with contant updates. If you face any issue, ensure you have updated ComfyUI to the latest version and update all requirements and share your workflow in the Issues. we are thankful to Harmonai-org and origianl repo for same🌈

Sample generator Tools to train a generative model on arbitrary audio samples

A big shout out and thanks to the wonderful work done on Sample diffusion by Harmonai and a lot of core code is ported from same to this repo and any queries on the working for same can be linked to the repo as shown here. sample-generator

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 of helper functions.

Nodes

Jags_Audiotools & Node summary

Node that the gives user the ability to generate and play audio results through variety of different methods.
Local models—The node pulls the required files from huggingface hub by default. You can create a models folder and place the modules there if you have a flaky connection or prefer to use it completely offline, it will load them locally instead. The path should be: ComfyUI/models/audio_diffusion; Alternatively, just clone the entire HF repo to it

Example Work flow

🎸ComfyUI_Jags_Audiotools- WIKI

Link to the workflow and explanations : AUDIO TOOLS WIKI

Dependencies

check Notes for more information.

Install:

To install, drop the “_ComfyUI_Jags_Audiotools_” folder into the “_…\ComfyUI\ComfyUI\custom_nodes_” directory and restart UI.

But the best method is to install same from ComfyUI Manager (https://github.com/ltdrdata/ComfyUI-Manager) and search for this name in the Node list and install from there and restart the UI as it takes care of all the dependencies and installs and make it easy for you.