ComfyUI_CogView4_Wrapper

★ 54

文本到图像CogView4ComfyUI插件本地GPU加速

在ComfyUI中非官方集成CogView4，便于在本地NVIDIA GPU（建议≥16GB）上生成高质量文本到图像，支持自动下载模型与快速部署。

💡 在ComfyUI中使用CogView4生成高质量文本到图像结果。

🍴 5 Forks💻 Python🔄 2025-03-06

🔗 GitHub 原文

📦

网盘下载

复制链接后前往夸克网盘下载

https://pan.quark.cn/s/51137d50651f

📦 requirements.txt

numpy<2.0
pillow
torch
huggingface_hub
git+https://github.com/huggingface/diffusers.git

📄 README

ComfyUI_CogView4_Wrapper

The unofficial implementation of CogView4 project in ComfyUI.

Recommended to run on Nvidia GPU with VRAM of 16GB or more.

Install

Open the cmd window in the plugin directory of ComfyUI, like “ComfyUI\custom_nodes“，type

git clone https://github.com/chflame163/ComfyUI_CogView4_Wrapper.git

Install dependency packages：

pip install -r ComfyUI_CogView4_Wrapper/requirements.txt

The model will be automatically downloaded to the “ComfyUI/models/CogView/CogView4-6B“ directory during the first run.

You can also manually download the model from huggingface.co/THUDM/CogView4-6B or BaiduNetdisk to the above directory.

Note

ComfyUI_CogView4_Wrapper requires the installation of the diffusers dependency package in dev version, which may affect certain plugins. Please be aware of backing up the environment.

statement

This nodes follows the MIT license, Some of its functional code comes from other open-source projects. Thanks to the original author. If used for commercial purposes, please refer to the original project license to authorization agreement.