VocalSeparation-ComfyUI

VocalSeparation-ComfyUI
★ 26

音频分离人声提取ComfyUI节点模型自动下载
ComfyUI自定义节点,用于将混合音乐中人声与伴奏分离,基于ZFTurbo训练的模型并自动下载权重,便于音频后期处理。
💡 在ComfyUI流程中将歌曲分离为人声和伴奏以便后期处理。
🍴 5 Forks💻 Python🔄 2024-10-24
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/b6135d9bd930
📦 requirements.txt
numpy
pandas
scipy
ml_collections
tqdm
segmentation_models_pytorch
timm
audiomentations
pedalboard
omegaconf
beartype
rotary_embedding_torch
einops
demucs
transformers
torchmetrics
spafe
protobuf
torch_audiomentations
asteroid
auraloss
torchseg
📄 README

VocalSeparation-ComfyUI

a custom node for separation vocals from music based on ZFTurbo/Music-Source-Separation-Training

How to use

## in ComfyUI/custom_nodes
git clone https://github.com/AIFSH/VocalSeparation-ComfyUI.git
cd VocalSeparation-ComfyUI
pip install -r requirements.txt

weights will be downloaded from github automatically