Check that your NVIDIA DGX Spark device meets the requirements before proceeding with installation.
python3 --version
pip3 --version
nvcc --version
nvidia-smi
Expected output should show Python 3.8+, pip available, CUDA toolkit, and GPU detection.
You will install ComfyUI on your host system, so you should create an isolated environment to avoid conflicts with system packages.
python3 -m venv comfyui-env
source comfyui-env/bin/activate
Verify the virtual environment is active by checking the command prompt shows (comfyui-env).
Install PyTorch with CUDA 13.0 support.
pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu130
This installation targets CUDA 13.0 compatibility with Blackwell architecture GPUs.
Download the ComfyUI source code from the official repository.
git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI/
Install the required Python packages for ComfyUI operation.
pip install -r requirements.txt
This installs all necessary dependencies including web interface components and model handling libraries.
Navigate to the checkpoints directory and download the Stable Diffusion 1.5 model.
cd models/checkpoints/
wget https://huggingface.co/Comfy-Org/stable-diffusion-v1-5-archive/resolve/main/v1-5-pruned-emaonly-fp16.safetensors
cd ../../
The download will be approximately 2GB and may take several minutes depending on network speed.
Start the ComfyUI web server with network access enabled.
python main.py --listen 0.0.0.0
The server will bind to all network interfaces on port 8188, making it accessible from other devices.
Check that ComfyUI is running correctly and accessible via your web browser.
curl -I http://localhost:8188
Expected output should show HTTP 200 response indicating the web server is operational.
Open a web browser and navigate to http://<SPARK_IP>:8188 where <SPARK_IP> is your device's IP address.
If you need to remove the installation completely, follow these steps:
WARNING
This will delete all installed packages and downloaded models.
deactivate
rm -rf comfyui-env/
rm -rf ComfyUI/
To rollback during installation, press Ctrl+C to stop the server and remove the virtual environment.
Test the installation with a basic image generation workflow:
http://<SPARK_IP>:8188nvidia-smi in a separate terminalThe image generation should complete within 30-60 seconds depending on your hardware configuration.