ComfyUI Linux Installation Tutorial

This comprehensive guide explains how to install and configure ComfyUI on Linux systems, including environment setup, comfy-cli installation, dependency configuration, and more to help users quickly set up their AI image generation environment.

⚠️ Important Notice: Installation steps may change as ComfyUI evolves. For the most up-to-date information, always check the official repository. This guide reflects current best practices as of mid-2025.

ℹ️ Note about updates: For the most up-to-date Desktop installation info, check the official docs.

There are two ways to install ComfyUI on Linux:

  1. Comfy CLI (Recommended) — Official command-line tool for easy installation
  2. Manual installation — Full control over the environment

Comfy Desktop: Linux is not officially supported at this time. Check the official docs for updates.

System Requirements

  • Python 3.12 or 3.13 (3.13 is recommended)
  • NVIDIA GPU with CUDA support, 4GB+ VRAM recommended
  • AMD GPU — ROCm 7.2 support (Linux only)
  • Intel GPU — Arc series via native PyTorch torch.xpu
  • RAM: 8 GB minimum, 16 GB recommended
  • Storage: SSD with at least 20 GB free space (bare minimum — models for typical workflows can easily consume 50–100GB+)

Comfy CLI is the official command-line tool that simplifies installation and management.

Step 1: Ensure Python Environment

Ensure Python 3.12 or 3.13 is installed:

python3 --version

If Python is not installed or the version is too old:

On Ubuntu/Debian: ```bash sudo apt update && sudo apt install python3 python3-pip python3-venv -y ```

On Arch Linux:

sudo pacman -S python python-pip

Step 2: Install Comfy CLI

pip install comfy-cli

Step 3: Install ComfyUI

comfy install

This command downloads and sets up ComfyUI with default settings. For more options, see the Complete Comfy CLI Guide.

Step 4: Launch ComfyUI

comfy launch

Navigate to http://127.0.0.1:8188 in your browser.

Method 3: Manual Installation

Step 1: Install Dependencies

Install system dependencies:

# Ubuntu/Debian
sudo apt update
sudo apt install git python3 python3-pip python3-venv -y

# Install NVIDIA GPU dependencies
# Ensure you have the NVIDIA driver and CUDA toolkit installed

Step 2: Clone the Repository

git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI

Step 3: Create Virtual Environment

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

Step 4: Install GPU and ComfyUI Dependencies

# Install PyTorch with CUDA 13.0
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130

# Install ComfyUI dependencies
pip install -r requirements.txt
# Install PyTorch with ROCm support
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.2

# Install ComfyUI dependencies
pip install -r requirements.txt
# Install PyTorch with Intel GPU support
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130

# Intel Arc support requires additional configuration
# See: https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#manual-install-windows-linux

Step 5: Start ComfyUI

python main.py

For AMD GPUs or CPU-only mode:

python main.py --cpu

For more startup options, see the ComfyUI Startup Flags guide.

Step 6: Access the UI

Open your browser and navigate to http://127.0.0.1:8188.

Next Steps