LogoWonderful Launcher
  • Home
  • Pricing
  • Docs
  • Download

Manual Install

Needs verification

Install ComfyUI manually from source for full control.

Manual installation gives you full control over your Python environment, PyTorch version, and CUDA configuration. This method is recommended for developers and advanced users.

Use PyTorch as the source of truth

PyTorch wheel combinations change faster than most ComfyUI guides. Use the PyTorch Start Locally tool as the final source of truth for your current Python, CUDA, ROCm, and platform combination. The commands below are the common combinations this page is designed around.

Prerequisites

Install these before starting:

  1. Python 3.12 or 3.13 (3.13 recommended) — Download from python.org
    • During install, check "Add Python to PATH"
  2. Git — Download from git-scm.com
  3. NVIDIA GPU drivers — Download from nvidia.com

Step 1: Clone the Repository

Open Command Prompt or PowerShell:

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

Step 2: Create a Virtual Environment (Recommended)

python -m venv venv
venv\Scripts\activate

You should see (venv) at the start of your command prompt.

Step 3: Install PyTorch

Install PyTorch with the CUDA version that matches your NVIDIA driver. First, check your driver version:

nvidia-smi

Then choose the right PyTorch install command:

NVIDIA GPU — CUDA Version Matching

Driver VersionCUDA VersionPyTorch Command
560+CUDA 12.6python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu126
570+CUDA 12.8python -m pip install torch==2.8.0 torchvision==0.23.0 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu128
575+CUDA 13.0python -m pip install torch==2.9.1 torchvision==0.24.1 torchaudio==2.9.1 --index-url https://download.pytorch.org/whl/cu130

RTX 50 Series Users

RTX 5070 Ti / 5080 / 5090 require CUDA 12.8 or higher. Make sure your driver is version 570+, and use the CUDA 12.8 or 13.0 PyTorch build. See GPU Compatibility for the full driver-CUDA-PyTorch matrix.

If you're unsure, the CUDA 12.6 build works for most RTX 20/30/40 series cards:

python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu126

AMD GPU (Linux with ROCm)

python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.2.4

CPU Only

python -m pip install torch torchvision torchaudio

Step 4: Install Dependencies

Do not run pip install -r requirements.txt blindly.

  1. Confirm which Python environment is active (where python or which python)
  2. Inspect requirements.txt — check if it pins torch, numpy, or opencv versions
  3. Install only the missing package when possible: pip install <package-name>
  4. Run pip check after installation to verify no conflicts were introduced
python -m pip install -r requirements.txt

Faster alternative: uv

uv is a much faster Python package installer (written in Rust). If you install it, you can replace many python -m pip install commands with uv pip install for faster downloads:

python -m pip install uv
uv pip install -r requirements.txt

Step 5: Download a Model

Place at least one checkpoint model in models/checkpoints/:

ComfyUI/
└── models/
    └── checkpoints/    ← Put your .safetensors file here

See Download Models for model recommendations.

Step 6: Run ComfyUI

python main.py

Once you see Starting server, open http://127.0.0.1:8188 in your browser.

Using comfy-cli (Alternative)

comfy-cli is a command-line tool that automates the manual install process:

pip install comfy-cli
comfy install

This handles cloning, virtual environment creation, PyTorch installation, and dependency setup in one command.

Updating

cd ComfyUI
git pull

Do not run pip install -r requirements.txt blindly.

  1. Confirm which Python environment is active (where python or which python)
  2. Inspect requirements.txt — check if it pins torch, numpy, or opencv versions
  3. Install only the missing package when possible: pip install <package-name>
  4. Run pip check after installation to verify no conflicts were introduced

If git pull fails, new features do not appear, or you need to downgrade to a known commit or stable tag, use ComfyUI Won't Update or Need to Downgrade before changing packages.

Troubleshooting

ProblemSolution
python command not foundReinstall Python with "Add to PATH" checked, or use python3
CUDA not available after PyTorch installPyTorch CUDA version doesn't match your driver. Check with nvidia-smi and reinstall the matching PyTorch
ModuleNotFoundErrorMake sure your venv is activated and run python -m pip install -r requirements.txt
Frontend package missing after updateSee ComfyUI Frontend Package
Build errors during pip installInstall Visual Studio Build Tools — some packages need a C++ compiler
torch.cuda.OutOfMemoryErrorRun with python main.py --lowvram
ComfyUI uses the wrong GPUChoose the device with ComfyUI Multi GPU

Next Steps

  • Generate your first image
  • Download models
  • Install custom nodes
  • System requirements
  • ComfyUI Won't Update
  • ComfyUI Multi GPU
  • Troubleshoot common issues

Source References

  • Official ComfyUI manual installation guide
  • PyTorch Start Locally installer
  • ComfyUI system requirements
  • ComfyUI GitHub repository

Start with Wonderful Launcher if this issue touches your real ComfyUI environment. Use the docs to understand the fix, and use the app to inspect the machine you already have.

Download Wonderful Launcher

Did this fix your issue?

Your answer helps prioritize verified ComfyUI repairs.

Table of Contents

Prerequisites
Step 1: Clone the Repository
Step 2: Create a Virtual Environment (Recommended)
Step 3: Install PyTorch
NVIDIA GPU — CUDA Version Matching
AMD GPU (Linux with ROCm)
CPU Only
Step 4: Install Dependencies
Step 5: Download a Model
Step 6: Run ComfyUI
Using comfy-cli (Alternative)
Updating
Troubleshooting
Next Steps
Source References