ComfyUI Deployment Guide

Key Features

Node-based visual workflow builder
Support for SD 1.5, SDXL, and more
CPU and GPU acceleration options
Extensible with custom nodes

Prerequisites

Before starting, ensure you have:

CPU-Only Requirements

• 4 CPU cores minimum
• 8GB RAM (16GB recommended)
• 50GB storage (more for models)
• Ubuntu 22.04 or 24.04 LTS

→ View Standard Cloud VPS Plans

GPU Requirements

• RamNode GPU VPS instance
• NVIDIA GPU with 8GB+ VRAM
• 16GB+ system RAM
• 100GB+ storage recommended

→ View GPU VPS Plans

Initial Server Setup

Update System & Install Dependencies

Install Dependencies

sudo apt update && sudo apt upgrade -y
sudo apt install -y git python3 python3-pip python3-venv wget curl \
  libgl1-mesa-glx libglib2.0-0 libsm6 libxext6 libxrender-dev

Create Dedicated User

Create ComfyUI User

sudo useradd -m -s /bin/bash comfyui
sudo passwd comfyui
sudo usermod -aG sudo comfyui
su - comfyui

Installation

Clone Repository & Setup Environment

Clone ComfyUI

cd /home/comfyui
git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI
python3 -m venv venv
source venv/bin/activate

CPU-Only Installation

Install PyTorch for CPU

CPU PyTorch Installation

pip install --upgrade pip
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
pip install -r requirements.txt

GPU Installation (NVIDIA)

Install NVIDIA Drivers & CUDA

Install CUDA Toolkit

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
sudo apt update
sudo apt install -y cuda-toolkit-12-4 nvidia-driver-550

Reboot & Verify

Verify GPU

sudo reboot
nvidia-smi

Install PyTorch with CUDA

GPU PyTorch Installation

pip install --upgrade pip
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
pip install -r requirements.txt

Model Setup

Download Stable Diffusion Checkpoint

Download SD 1.5 Model

cd /home/comfyui/ComfyUI/models/checkpoints
wget -O sd_v1-5.safetensors "https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors"

ℹ️ For SDXL or other models, place them in the same directory. VAE files go in models/vae/ and LoRA files in models/loras/.

Systemd Service

Create Service File

Create Systemd Service

sudo nano /etc/systemd/system/comfyui.service

Service Configuration

/etc/systemd/system/comfyui.service

[Unit]
Description=ComfyUI Stable Diffusion Interface
After=network.target

[Service]
Type=simple
User=comfyui
Group=comfyui
WorkingDirectory=/home/comfyui/ComfyUI
Environment="PATH=/home/comfyui/ComfyUI/venv/bin:/usr/local/bin:/usr/bin:/bin"
ExecStart=/home/comfyui/ComfyUI/venv/bin/python main.py --listen 127.0.0.1 --port 8188
Restart=on-failure
RestartSec=10

[Install]
WantedBy=multi-user.target

⚠️ For CPU-only deployments, add --cpu to the ExecStart line.

Enable & Start Service

Enable Service

sudo systemctl daemon-reload
sudo systemctl enable comfyui
sudo systemctl start comfyui
sudo systemctl status comfyui

Nginx Reverse Proxy

Install Nginx

sudo apt install -y nginx
sudo nano /etc/nginx/sites-available/comfyui

Nginx Configuration

/etc/nginx/sites-available/comfyui

server {
    listen 80;
    server_name your-domain.com;
    client_max_body_size 100M;

    location / {
        proxy_pass http://127.0.0.1:8188;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "upgrade";
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
        proxy_read_timeout 300s;
        proxy_connect_timeout 300s;
        proxy_send_timeout 300s;
    }
}

Enable Site

Enable Nginx Site

sudo ln -s /etc/nginx/sites-available/comfyui /etc/nginx/sites-enabled/
sudo rm /etc/nginx/sites-enabled/default
sudo nginx -t
sudo systemctl restart nginx

SSL Configuration

Install Certbot & Get Certificate

SSL Setup

sudo apt install -y certbot python3-certbot-nginx
sudo certbot --nginx -d your-domain.com

Basic Authentication

Add HTTP Basic Auth

Since ComfyUI lacks built-in authentication, add HTTP basic auth:

Create Password File

sudo apt install -y apache2-utils
sudo htpasswd -c /etc/nginx/.htpasswd comfyui_admin

Update Nginx Location Block

Add Auth to Nginx

location / {
    auth_basic "ComfyUI Access";
    auth_basic_user_file /etc/nginx/.htpasswd;
    # ... rest of proxy configuration
}

Reload Nginx

sudo systemctl reload nginx

Firewall Configuration

Configure UFW

Setup Firewall

sudo ufw default deny incoming
sudo ufw default allow outgoing
sudo ufw allow ssh
sudo ufw allow 80/tcp
sudo ufw allow 443/tcp
sudo ufw enable

Performance Optimization

CPU-Only Tuning

For CPU deployments, adjust the systemd ExecStart for better performance:

CPU ExecStart

ExecStart=/home/comfyui/ComfyUI/venv/bin/python main.py --listen 127.0.0.1 --port 8188 --cpu --lowvram

Memory Management

For systems with limited RAM, add swap space:

Add Swap Space

sudo fallocate -l 8G /swapfile
sudo chmod 600 /swapfile
sudo mkswap /swapfile
sudo swapon /swapfile
echo '/swapfile none swap sw 0 0' | sudo tee -a /etc/fstab

Installing Custom Nodes

Install ComfyUI-Manager

Install Manager

cd /home/comfyui/ComfyUI/custom_nodes
git clone https://github.com/ltdrdata/ComfyUI-Manager.git
sudo systemctl restart comfyui

ℹ️ Access the Manager through the ComfyUI interface to browse and install additional nodes.

Maintenance

Updating ComfyUI

Update ComfyUI

sudo systemctl stop comfyui
cd /home/comfyui/ComfyUI
source venv/bin/activate
git pull
pip install -r requirements.txt --upgrade
sudo systemctl start comfyui

Log Monitoring

View Logs

sudo journalctl -u comfyui -f

Backup Script

#!/bin/bash
BACKUP_DIR="/home/comfyui/backups/$(date +%Y%m%d)"
mkdir -p "$BACKUP_DIR"
cp -r /home/comfyui/ComfyUI/models "$BACKUP_DIR/"
cp -r /home/comfyui/ComfyUI/user "$BACKUP_DIR/"
cp -r /home/comfyui/ComfyUI/custom_nodes "$BACKUP_DIR/"

Troubleshooting

Issue	Solution
Out of memory errors	Add --lowvram or --novram flags. For CPU mode, reduce image dimensions.
Slow generation on CPU	Expected behavior. Use smaller models like SD 1.5 over SDXL.
WebSocket issues	Verify Nginx proxy includes WebSocket upgrade headers.
Model loading failures	Verify model files are complete. Use .safetensors format.

Deploying ComfyUI on RamNode VPS