【生成模型】【ComfyUI（一）】Flux与Flux-Fill部署与API调用

ComfyUI安装

基础

conda create -n imggen-cu118 python=3.10.14
conda activate imggen-cu118

# torch
conda install pytorch==2.5.0 torchvision==0.20.0 torchaudio==2.5.0  pytorch-cuda=11.8 -c pytorch -c nvidia

mkdir projects && cd projects
git clone https://github.com/comfyanonymous/ComfyUI
cd ComfyUI
pip install -r requirements.txt

CUDA_VISIBLE_DEVICES=1 python main.py --listen $your_server_ip --port 8081 &
# 查看日志：tail -f user/comfyui_8081.log

# node: ComfyUI Manager, 方便节点的install, remove, disable, and enable 
cd custom_nodes/
git clone https://github.com/ltdrdata/ComfyUI-Manager.git

# 通过Manager => Custom Nodes Manger安装
ComfyUI Nodes for External Tooling  # comfyui-tooling-nodes
ComfyUI Essentials   # Node:Mask Previews+ 
net tool node for comfyui  # comfyui-tooling-nodes => Node:LoadImageBase64

常用节点

1. ComfyUI Manager
   https://blog.csdn.net/2401_84760527/article/details/140261908
   通过这个节点，我们可以管理安装节点（模型checkpoint, lora, vae, encoder, controlnet）
   

快捷方式

工作流

Flux

工作流图片（可直接拖拽到ComfyUI中）：

• Flux-Schnell-comfyorg-fp8