整合包下载。中国用户且为windows（NVIDIA显卡用户）可直接使用我的整合包，包含所有模型和插件。

1. 百度网盘链接：https://pan.baidu.com/s/1GJBOqlNXcU0kMdYCPJ5qsw?pwd=11ws 提取码：11ws
2. 夸克网盘：https://pan.quark.cn/s/4a511208b05e

ComfyUI Setup and Workflow for Figma-to-Image Generation

Note: Due to limited resources, I have only tested ComfyUI on Windows（Nvidia GPU with 16GVRAM）. Mac and Linux platforms have not been fully tested.

Installing ComfyUI

Important: The Figma-to-image workflow requires uploading Figma images to the input folder within the ComfyUI directory. Ensure the input folder path is as follows: ComfyUI/input/. If you're unsure about setting paths, I strongly recommend using the portable version of ComfyUI!

1. Open the official GitHub repository and follow the installation instructions: https://github.com/comfyanonymous/ComfyUI. I recommend downloading the official portable package: https://github.com/comfyanonymous/ComfyUI/releases
2. After installation, run a basic text-to-image workflow to ensure it functions correctly.
3. Keep the ComfyUI address unchanged: http://127.0.0.1:8188. The plugin's service address currently only supports this address.

Enabling -enable-cors-header

This allows external access to ComfyUI. Here's how:

Default ComfyUI Version

Modify the startup parameters:

python main.py --enable-cors-header

Portable Version

Modify the run_nvidia_gpu.bat file:

.\\python_embeded\\python.exe -s ComfyUI\\main.py --enable-cors-header --windows-standalone-build
pause

Downloading ComfyUI Plugins

I used the following plugins for this workflow: