快速开始

# 克隆工程
git clone https://github.com/comfyanonymous/ComfyUI.git

cd ComfyUI

python3.12 -m venv venv
source venv/bin/activate

# 在Mac上加速PyTorch训练 https://developer.apple.com/metal/pytorch/
pip3 install --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cpu

pip install -r requirements.txt

python main.py

安装插件

ComfyUI Manager

cd ComfyUI/custom_nodes
git clone https://github.com/Comfy-Org/ComfyUI-Manager.git

ComfyUI-Align

cd ComfyUI/custom_nodes
git clone https://github.com/Moooonet/ComfyUI-Align.git

ComfyUI-VideoHelperSuite

cd ComfyUI/custom_nodes
git clone https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite.git
cd ComfyUI-VideoHelperSuite
pip install -r requirements.txt

相关项目

CosyVoice-ComfyUI

定制音色。

工作流

SD3.5L IPAdapter

这是一个使用 Stable Diffusion 3.5 Large 模型和 IPAdapter 进行图像生成的工作流。

相关插件：

• ComfyUI-IPAdapter-SD3
• ComfyUI-Easy-Use [非必须]

相关模型：

• sd3.5_large.safetensors
  • SHA256: ffef7a279d9134626e6ce0d494fba84fc1c7e720b3c7df2d19a09dc3796d8f93
• clip_g.safetensors
  • SHA256: ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
• clip_l.safetensors
  • SHA256: 660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
• t5xxl_fp16.safetensors
  • SHA256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
• ip-adapter.bin [SD3.5]
  • SHA256: 9fe54774aa528e712d9145ff6a59dd93b1fcf1d5935304feffd980ae6d42ae03
• sigclip_vision_patch14_384.safetensors
  • SHA256: 1fee501deabac72f0ed17610307d7131e3e9d1e838d0363aa3c2b97a6e03fb33

测试图片：

Flux.1 dev

这是一个简单的 Flux 工作流测试，用于生成图像。不需要任何插件。

相关模型：

• flux1-dev.safetensors
  • SHA256: 4610115bb0c89560703c892c59ac2742fa821e60ef5871b33493ba544683abd7
• split_files/vae/ae.safetensors
  • SHA256: afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
• t5xxl_fp16.safetensors
  • SHA256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
• clip_l.safetensors
  • SHA256: 660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd