ComfyUI-ThinkSound

ComfyUI-ThinkSound is now available in ComfyUI, ThinkSound is a unified Any2Audio generation framework with flow matching guided by Chain-of-Thought (CoT) reasoning.

By Yuan-ManX·Created about a year ago·Updated about a year ago· 29

Yuan-ManX/ComfyUI-ThinkSound

Nodes4

On cloudLocal install

CategoryThinkSound

Stars29

Updatedabout a year ago

Nodes (4)

Load Caption

The tiny node that names your ThinkSound scene

ThinkSound

Load CoT Description

Where you actually write the sound design

ThinkSound

LoadO ThinkSound Video

The node that's really just a file path

ThinkSound

The node that gives silent video a soundtrack (and why it's half-baked)

ThinkSound

Readme

ComfyUI-ThinkSound

ComfyUI-ThinkSound is now available in ComfyUI, ThinkSound is a unified Any2Audio generation framework with flow matching guided by Chain-of-Thought (CoT) reasoning.

Installation

Make sure you have ComfyUI installed
Clone this repository into your ComfyUI's custom_nodes directory:

cd ComfyUI/custom_nodes
git clone https://github.com/Yuan-ManX/ComfyUI-ThinkSound.git

Install dependencies:

cd ComfyUI-ThinkSound

# Install dependencies
pip install -r requirements.txt
conda install -y -c conda-forge 'ffmpeg<7'

Model

Download Pretrained Models

# Download pretrained weights https://huggingface.co/liuhuadai/ThinkSound to Directory ckpts/
# model weights can be also downloaded from https://www.modelscope.cn/models/iic/ThinkSound
git lfs install
git clone https://huggingface.co/liuhuadai/ThinkSound ckpts