2025-02-24 17:52:19 +08:00
2025-02-24 17:52:19 +08:00
2025-02-24 10:08:40 +08:00
2025-02-24 09:55:18 +08:00
2025-02-24 09:55:18 +08:00
2025-02-23 05:48:21 +08:00
2025-02-24 17:50:16 +08:00
2025-02-24 11:22:38 +08:00

CosyVoice2_ComfyUI

A plugin of ComfyUI for CosyVoice2,
one component for text to long Sonic video in ComfyUI.

Installation

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

git clone https://github.com/benda1989/CosyVoice2_ComfyUI.git
cd CosyVoice2_ComfyUI
conda install -y -c conda-forge pynini==2.1.5
pip install -r requirements.txt
# If you encounter sox compatibility issues
# ubuntu
sudo apt-get install sox libsox-dev
# centos
sudo yum install sox sox-devel 

Copy models

By default project will download CosyVoice2-0.5B and CosyVoice-ttsfrd into pretrained_models,
You can copy it there if you downloaded before.
file tree looks like this at least:

--  ComfyUI/custom_node/CosyVoice2_ComfyUI/pretrained_models
    |-- CosyVoice2-0.5B
    |-- CosyVoice-ttsfrd

Example

S
Description
No description provided
Readme
1.6 MiB
Languages
Python 99.8%
Shell 0.2%