14 KiB
Installing ComfyUI
This is the long form install reference: every GPU vendor, every accelerator, and the post-install options that are easy to miss.
Note: most people do not need this page. The desktop app is the easiest and best way to use ComfyUI, and comfy-cli (
pip install comfy-cli && comfy install) covers most of the rest.
Visit the README for a condensed version of the install options.
Or visit the Manual Installation guide on Comfy Docs for additional installation instructions with navigation and translations.
Contents
- Manual install (Windows, Linux)
- Windows Portable
- ComfyUI-Manager
- Running
- Sharing models with another UI
- High-quality previews
- TLS/SSL
Manual install (Windows, Linux)
Python 3.14 works but some custom nodes may have issues. The free threaded variant works but some dependencies will enable the GIL so it's not fully supported.
Python 3.13 is very well supported. If you have trouble with some custom node dependencies on 3.13 you can try 3.12.
torch 2.7 is minimally supported but using a newer version is extremely recommended. Using a cu130 or above version of pytorch is required on Nvidia 20 series and above. Some features and optimizations might only work on newer versions. We generally recommend using the latest major version of pytorch with the latest cuda version unless it is less than 2 weeks old. If your pytorch is more than 6 months old, please update it.
Instructions
Git clone this repo:
git clone https://github.com/Comfy-Org/ComfyUI.git
Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints
Put your VAE in: models/vae
Then install PyTorch for your hardware using the relevant section below, install the
dependencies, and launch with python main.py.
NVIDIA
Nvidia users should install stable pytorch using this command:
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130
This is the command to install pytorch nightly instead which might have performance improvements:
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu132
Troubleshooting
If you get the "Torch not compiled with CUDA enabled" error, uninstall torch with:
pip uninstall torch
Then install it again with the stable command from above:
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130
AMD GPUs (Linux)
AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.2
This is the command to install the nightly with ROCm 7.2 which might have some performance improvements:
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.2
AMD GPUs (Windows, ROCm 10.0)
Use AMD's multi-architecture PyTorch packages.
The device-* extras install your GPU's kernels and the matching ROCm runtime
automatically; a separate HIP SDK installation is not needed.
Use Windows 11, a current AMD graphics driver, and 64-bit Python 3.13.
The install command below uses device-all to install kernels for all supported GPUs. To
reduce download size and disk usage, optionally replace both occurrences of
device-all with the target for your GPU:
| GPU | Device extra |
|---|---|
| RX 9070 / XT, Radeon AI PRO R9700 | device-gfx1201 |
| RX 9060 / XT | device-gfx1200 |
| RX 7900 XT / XTX | device-gfx1100 |
| RX 7700 XT / 7800 XT | device-gfx1101 |
| RX 7600 / XT | device-gfx1102 |
| Ryzen AI Max / Max+ (Strix Halo) | device-gfx1151 |
Note: This table only lists examples. A GPU missing from it may still be supported:
supported architectures include RDNA 2, RDNA 3, RDNA 3.5, and RDNA 4. Keep device-all
to install kernels for all supported targets. For other models, see AMD's
GPU target table
and ROCm compatibility matrix.
ROCm 10.0.0 with PyTorch 2.13:
pip install --index-url https://stable.repo.amd.com/rocm/whl-next/ "torch[device-all]==2.13.0+rocm10.0.0" "torchvision[device-all]==0.28.0+rocm10.0.0" "torchaudio==2.11.0.2+rocm10.0.0"
Intel GPUs (Windows and Linux)
Intel Arc GPU users can install native PyTorch with torch.xpu support using pip. More information can be found here.
To install PyTorch xpu, use the following command:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu
This is the command to install the Pytorch xpu nightly which might have some performance improvements:
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/xpu
See also Intel GPU issues in the troubleshooting docs.
Apple Mac silicon
You can install ComfyUI in Apple Mac silicon (M1, M2, M3 or M4) with any recent macOS version.
- Install pytorch nightly. For instructions, read the Accelerated PyTorch training on Mac Apple Developer guide (make sure to install the latest pytorch nightly).
- Follow the manual installation instructions above.
- Install the ComfyUI dependencies.
- Launch ComfyUI by running
python main.py.
Note
: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in manual installation.
Huawei Ascend NPUs
For models compatible with Huawei Ascend Extension for PyTorch (torch_npu). To get started, ensure your environment meets the prerequisites outlined on the installation page. Here's a step-by-step guide tailored to your platform and installation method:
- Begin by installing the recommended or newer kernel version for Linux as specified in the Installation page of torch-npu, if necessary.
- Proceed with the installation of Ascend Basekit, which includes the driver, firmware, and CANN, following the instructions provided for your specific platform.
- Next, install the necessary packages for torch-npu by adhering to the platform-specific instructions on the Installation page.
- Finally, adhere to the manual installation guide for Linux. Once all components are installed, you can run ComfyUI as described earlier.
Cambricon MLUs
For models compatible with Cambricon Extension for PyTorch (torch_mlu). Here's a step-by-step guide tailored to your platform and installation method:
- Install the Cambricon CNToolkit by adhering to the platform-specific instructions on the Installation page.
- Next, install the PyTorch(torch_mlu) following the instructions on the Installation page.
- Launch ComfyUI by running
python main.py.
Iluvatar Corex
For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step guide tailored to your platform and installation method:
- Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the Installation page.
- Launch ComfyUI by running
python main.py.
Dependencies
Install the dependencies by opening your terminal inside the ComfyUI folder and:
pip install -r requirements.txt
After this you should have everything installed and can proceed to running ComfyUI.
Windows Portable
Note: the portable build is not recommended for regular users, who should use the desktop app instead.
There is a portable standalone build for Windows, with a version for each GPU vendor. Any of them will also run on your CPU alone.
Pick the one matching your GPU:
| GPU | Download |
|---|---|
| Nvidia | ComfyUI_windows_portable_nvidia.7z |
| AMD | ComfyUI_windows_portable_amd.7z |
| Intel | ComfyUI_windows_portable_intel.7z |
On a GTX 10 series or older Nvidia GPU? Those cards need the legacy cu126 build instead, which ships python 3.12 and pytorch cuda 12.6.
Simply download, extract with 7-Zip or with the windows explorer on
recent windows versions and run. For smaller models you normally only need to put the
checkpoints (the huge ckpt/safetensors files) in ComfyUI\models\checkpoints, but many
of the larger models have multiple files. Make sure to follow the instructions to know
which subfolder to put them in under ComfyUI\models\.
If you have trouble extracting it, right click the file -> properties -> unblock.
To run on your CPU alone, the Nvidia build ships advanced\run_cpu.bat. The AMD and
Intel builds have no CPU launcher, so open a terminal in the extracted folder and run:
.\python_embeded\python.exe -s ComfyUI\main.py --cpu --windows-standalone-build
The Nvidia build above comes with python 3.13 and pytorch cuda 13.0. Update your Nvidia drivers if it doesn't start.
ComfyUI-Manager
ComfyUI-Manager is an extension that allows you to easily install, update, and manage custom nodes for ComfyUI.
Note: the desktop app comes with ComfyUI-Manager already set up. The steps below are only needed for manual and portable installs.
-
Install the manager dependencies:
pip install -r manager_requirements.txt -
Enable the manager with the
--enable-managerflag when running ComfyUI:python main.py --enable-manager
Command line options
| Flag | Description |
|---|---|
--enable-manager |
Enable ComfyUI-Manager |
--enable-manager-legacy-ui |
Use the legacy manager UI instead of the new UI (implies --enable-manager) |
--disable-manager-ui |
Disable the manager UI and endpoints while keeping background features like security checks and scheduled installation completion (requires --enable-manager) |
See the manager docs for full configuration.
Running
python main.py
The full list of launch options is documented at docs.comfy.org/development/comfyui-server/startup-flags.
For AMD cards not officially supported by ROCm
Try running it with this command if you have issues:
For 6700, 6600 and maybe other RDNA2 or older:
HSA_OVERRIDE_GFX_VERSION=10.3.0 python main.py
For AMD 7600 and maybe other RDNA3 cards:
HSA_OVERRIDE_GFX_VERSION=11.0.0 python main.py
AMD ROCm tips
You can try setting this env variable PYTORCH_TUNABLEOP_ENABLED=1 which might speed
things up at the cost of a very slow initial run.
Sharing models with another UI
See the config file to set the search paths for
models. In the standalone windows build you can find this file in the ComfyUI directory.
Rename this file to extra_model_paths.yaml and edit it with your favorite text editor.
High-quality previews
Use --preview-method auto to enable previews.
The default installation includes a fast latent preview method that's low-resolution. To
enable higher-quality previews with TAESD,
download the taesd_decoder.pth, taesdxl_decoder.pth, taesd3_decoder.pth and
taef1_decoder.pth and place them in the
models/vae_approx folder. Once they're installed, restart ComfyUI and launch it with
--preview-method taesd to enable high-quality previews.
TLS/SSL
Generate a self-signed certificate (not appropriate for shared/production use) and key by running the command:
openssl req -x509 -newkey rsa:4096 -keyout key.pem -out cert.pem -sha256 -days 3650 -nodes -subj "/C=XX/ST=StateName/L=CityName/O=CompanyName/OU=CompanySectionName/CN=CommonNameOrHostname"
Use --tls-keyfile key.pem --tls-certfile cert.pem to enable TLS/SSL, the app will now be
accessible with https://... instead of http://....
Note: Windows users can use alexisrolland/docker-openssl or one of the 3rd party binary distributions to run the command example above.
If you use a container, note that the volume mount
-vcan be a relative path so... -v ".\:/openssl-certs" ...would create the key & cert files in the current directory of your command prompt or powershell terminal.