How to run ComfyUI on an NVIDIA 5090 GPU
Overview
These are my short notes on how to run ComfyUI on an NVIDIA 5090 GPU. The Blackwell architecture has been released Q4 2024, and is supported by nightly >= 12.8 PyTorch builds.
Common Error: If you get either of the following errors on a 5090 GPU, the solution is to use a nightly PyTorch build that supports CUDA capability sm_120:
CUDA error: no kernel image is available for execution on the deviceNVIDIA GeForce RTX 5090 with CUDA capability sm_120 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_70 sm_75 sm_80 sm_86 sm_90.
Also rule out an NVIDIA driver version mismatch between the nvidia-smi reported CUDA version and your installed PyTorch version.
Installation Steps
Clone the ComfyUI repository:
git clone https://github.com/comfyanonymous/ComfyUI.git .Install PyTorch and related packages:
. venv/bin/activate && pip install --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cu129 onnxruntime-gpu numba diffusersNotice we are using a nightly build for CUDA 12.9: https://download.pytorch.org/whl/nightly/cu129
Install ComfyUI dependencies:
. venv/bin/activate && pip install -r requirements.txtRun ComfyUI:
. venv/bin/activate && python main.py --listen 0.0.0.0Makefile
Here is a Makefile with all of the above:
all:
python3.10 -m venv venv
. venv/bin/activate && pip install --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cu129 onnxruntime-gpu numba diffusers
. venv/bin/activate && pip install opencv-contrib-python==4.8.1.78 opencv-python==4.8.1.78 opencv-python-headless==4.7.0.72
. venv/bin/activate && pip install -r requirements.txt
run:
. venv/bin/activate && python main.py --listen 0.0.0.0Run make all to install dependencies, and make run to start the web UI.
Docker Container
Here is the link to my ComfyUI Docker container: