ComfyUI_Demucs

ComfyUI_Demucs
★ 10

音频分离人声提取音乐制作ComfyUI节点
在ComfyUI中集成Demucs，实现音乐源分离，快速提取人声与伴奏（贝斯、鼓等）并提供界面化、简易操作，特定工作流可无需额外模型。
💡 在ComfyUI中一键分离混音，提取人声或伴奏
🍴 3 Forks💻 Python🔄 2025-12-12
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/c1eafc754fbb
📦 requirements.txt
#
please
make
sure
you
have
already
a
pytorch
install
that
is
cuda
enabled!
dora-search>=0.1.12
diffq>=0.2.1
einops
flake8
hydra-colorlog>=1.1
hydra-core>=1.1
julius>=0.2.3
lameenc>=1.2
museval
mypy
openunmix
pyyaml
submitit
torch>=1.8.1
torchaudio>=0.8,<2.1
tqdm
treetable
soundfile>=0.10.3;sys_platform=="win32"
📄 README

ComfyUI_Demucs

Using Demucs in comfyUI

Demucs 音频分离开源方法在comfyUI这个GUI上的简单实现；

**TIPS:

  • using workflow in dir,no need any models./简单用不需要模型；
  • mixed=bass+drums+other,input audio=bass+drums+other+vocal/合成好的分离音频是mixed（=bass+drums+other），人声是vocal；

    • 1.Installation

    In the ./ComfyUI /custom_node directory, run the following:

    git clone https://github.com/smthemex/ComfyUI_Demucs.git

    2.requirements

    pip install -r requirements_minimal.txt

    3.Example

    4.Citation

    facebookresearch/demucs