'

---
title: Using ComfyUI in LobeHub for Image Generation
description: Learn how to configure and use the ComfyUI service in LobeHub to support high-quality image generation and editing with the FLUX model series.
tags:
  - ComfyUI
  - FLUX
  - Text-to-Image
  - Image Editing
  - AI Image Generation
---

# Using ComfyUI in LobeHub

<Image alt={'Using ComfyUI in LobeHub'} cover src={'https://hub-apac-1.lobeobjects.space/docs/e9b811f248a1db2bd1be1af888cf9b9d.png'} />

This guide will walk you through how to use [ComfyUI](https://github.com/comfyanonymous/ComfyUI) in LobeHub for high-quality AI image generation and editing.

## Introduction to ComfyUI

ComfyUI is a powerful GUI for Stable Diffusion and Flow Diffusion, offering a node-based workflow interface. LobeHub integrates ComfyUI with full support for the FLUX model series, enabling both text-to-image generation and image editing.

### Key Features

- **Extensive Model Support**: Supports 223 models, including 130 FLUX and 93 SD models
- **Config-Driven Architecture**: Registry system enables intelligent model selection
- **Multi-Format Support**: Compatible with .safetensors and .gguf formats, with various quantization levels
- **Dynamic Precision Options**: Supports default, fp8_e4m3fn, fp8_e5m2, and fp8_e4m3fn_fast
- **Multiple Authentication Methods**: Supports None, Basic Auth, Bearer Token, and Custom Headers
- **Smart Component Selection**: Automatically selects optimal T5, CLIP, and VAE encoders
- **Enterprise-Grade Optimizations**: Includes NF4, SVDQuant, TorchAO, MFLUX variants

## Quick Start

### Step 1: Configure ComfyUI in LobeHub

#### 1. Open Settings

- Go to the `Settings` panel in LobeHub
- Under `AI Providers`, find the `ComfyUI` section

<Image alt={'ComfyUI Settings Panel'} inStep src={'/blog/assets17870709/3f31bc33-509f-4ad2-ba81-280c2a6ec5fa.webp'} />

#### 2. Set Connection Parameters

**Basic Configuration**:

- **Server Address**: Enter your ComfyUI server address, e.g., `http://localhost:8000`
- **Authentication Type**: Choose the appropriate method (default is None)

### Step 2: Select a Model and Generate Images

#### 1. Choose a FLUX Model

In the chat interface:

- Click the model selection button
- Choose your desired FLUX model from the ComfyUI category

<Image alt={'Select FLUX Model'} inStep src={'/blog/assets17870709/ff7ebacf-27f0-42d7-810b-00314499a084.webp'} />

#### 2. Text-to-Image Generation

**Using FLUX Schnell (Fast Generation)**:

```plaintext
Generate an image: A cute orange cat sitting on a sunny windowsill, warm lighting, detailed fur texture

Generate high quality image: City skyline at sunset, cyberpunk style, neon lights, 4K high resolution, detailed architecture

Edit this image: Change the background to a starry night sky, keep the main subject, cosmic atmosphere

Authentication Type: None
Server Address: http://localhost:8000

# Install apache2-utils
sudo apt-get install apache2-utils

# Create user 'admin'
sudo htpasswd -c /etc/nginx/.htpasswd admin

Authentication Type: Basic
Server Address: https://your-domain.com
Username: admin
Password: your_secure_password

import jwt
import datetime

payload = {
    'user': 'admin',
    'exp': datetime.datetime.utcnow() + datetime.timedelta(days=30)
}

secret_key = "your-secret-key"
token = jwt.encode(payload, secret_key, algorithm='HS256')
print(f"Bearer Token: {token}")

Authentication Type: Bearer Token
Server Address: https://your-domain.com
API Key: example-eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...

Authentication Type: Custom
Server Address: https://your-domain.com
Custom Headers:
{
  "X-API-Key": "your_api_key",
  "X-Client-ID": "LobeHub"
}

# Navigate to ComfyUI's custom_nodes directory
cd ComfyUI/custom_nodes

# Clone the Comfy-Manager repository
git clone https://github.com/ltdrdata/ComfyUI-Manager.git

# Restart the ComfyUI server
# After restarting, you should see a "Manager" button in the UI

# Run from the ComfyUI root directory
curl -fsSL https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/install.sh | bash