Manual Installation

System RequirementsPlease check the system requirements page to make sure your hardware is capable of running the desired models.

Are you in the right place?

Local Installation GuideIf you want to use Invoke locally, you should probably use the launcher instead.

Developer Installation GuideIf you want to contribute to InvokeAI or run the app on the main branch, follow the developer installation guide instead.

Your setup

Commands that differ by operating system or GPU are listed for every setup, each labeled with the setup it applies to.

Operating system

WindowsmacOSLinux

GPU

NVIDIAAMDIntel ArcOther / noneNone (CPU)ARM64Apple silicon

Showing commands for

Walkthrough

We’ll use uv to install python and create a virtual environment, then install the invokeai package. uv is a modern, very fast alternative to pip.

The following commands vary depending on the version of Invoke being installed and the system onto which it is being installed.

1. Install uv as described in its docs. We suggest using the standalone installer method.

   Run uv --version to confirm that uv is installed and working. After installation, you may need to restart your terminal to get access to uv.

2. Create a directory for your installation, typically in your home directory (e.g. ~/invokeai or $Home/invokeai):

   Windows

   mkdir $Home/invokeai
   cd $Home/invokeai

   macOS, Linux

   mkdir ~/invokeai
   cd ~/invokeai

3. Create a virtual environment in that directory:

   Every setup except Windows · ARM64

   uv venv --relocatable --prompt invoke --python 3.12 --python-preference only-managed .venv

   Windows · ARM64

   uv venv --relocatable --prompt invoke `
     --python cpython-3.12-windows-aarch64-none --python-preference only-managed .venv

   This command creates a portable virtual environment at .venv complete with a portable python 3.12. It doesn’t matter if your system has no python installed, or has a different version - uv will handle everything.

   Windows · ARM64

   Windows on ARM64 (RTX Spark)

   uv installs an x86_64 python on ARM64 Windows unless asked for the native build, and an x86_64 python cannot load the ARM64 torch, so this command requests the native interpreter explicitly. The install command below uses the same --python cpython-3.12-windows-aarch64-none in place of --python 3.12.

4. Activate the virtual environment:

   Windows

   .venv\Scripts\activate

   macOS, Linux

   source .venv/bin/activate

5. Choose a version to install.

   View Releases

6. Determine the package specifier to use when installing: invokeai, plus any of these extras in brackets, separated by commas.

   Windows, Linux · NVIDIA

   • cuda, if you use --torch-backend=cu130 in the next step (Nvidia GPU on Windows x64 or Linux x86_64). It installs the PyTorch build Invoke is tested with and, on Windows, Triton. Add it only for Invoke 7 or newer, and never with another torch backend: it pins PyTorch’s CUDA 13 build, which no other backend provides.
   • xformers, if you have an Nvidia 16xx or 20xx series GPU. This is a performance optimization.

   For example invokeai[cuda] for a 30xx series GPU or newer, or invokeai[cuda,xformers] for a 16xx or 20xx series GPU.

   Every setup except NVIDIA

   Use invokeai without extras. The cuda extra is only for --torch-backend=cu130 (Nvidia GPU on Windows x64 or Linux x86_64): it pins PyTorch’s CUDA 13 build, which no other backend provides. The xformers extra is only for Nvidia 16xx or 20xx series GPUs.

7. Determine the torch backend to use for installation, if any. This is necessary to get the right version of torch installed. This is achieved by using UV’s built in torch support.

   Torch Backend Selection

   Pick a torch backend only when it applies to your system. In all other cases, do not use a torch backend.

   Windows, Linux · NVIDIA

   Use:

   --torch-backend=cu130

   Windows, Linux · Intel Arc

   Use:

   --torch-backend=xpu

   Windows · AMD

   Do not use a torch backend. AMD publishes its ROCm wheels on its own index, with the GPU kernels in a separate package per GPU target. In the next step, pin them for your GPU’s target and point uv at that index instead.

   Linux · AMD

   Do not use a torch backend. In the next step, install AMD’s ROCm 10 wheels from AMD’s index, as the launcher does, with the GPU kernels pinned for your GPU’s target.

   ROCm 10 has no kernels for Vega-based cards (gfx900/gfx906). For those, use PyTorch’s ROCm 7.2 build instead:

   --torch-backend=rocm7.2

   ROCm and torch versions

   Prefer torch 2.13+ on the rocm7.2 index: its bundled attention kernels (AOTriton 0.12b) are around 3x faster on RDNA3 cards than the 2.10/rocm7.1 generation. torch 2.12.x on the older rocm7.1 index was reported to break generation (#9410); if you must stay on rocm7.1, also pass "torch<2.12" to constrain the resolver.

   Windows · ARM64

   Do not use a torch backend. torch comes from NVIDIA’s own index, and three packages that have no ARM64 build on PyPI (OpenCV, blake3, tiktoken) come from wheels Invoke publishes. Use these two options instead of --torch-backend:

   --index https://pypi.nvidia.com/nvtorch_oot/ --find-links https://github.com/invoke-ai/InvokeAI/releases/download/win-arm64-wheels-v1/index.html

   With or without an NVIDIA GPU: this is the only torch build for Windows ARM64. See the system requirements for the platform’s feature differences.

   Linux · None (CPU)

   On x86_64, use:

   --torch-backend=cpu

   On ARM64 (aarch64, e.g. Raspberry Pi 5), do not use a torch backend. The default PyPI wheels are CPU-only on ARM64 and work out of the box.

   Windows · Other / none

   Do not use a torch backend.

   macOS

   Do not use a torch backend.

8. Install the invokeai package. Substitute the package specifier and version.

   Windows · NVIDIA

   uv pip install "<PACKAGE_SPECIFIER>==<VERSION>" `
     --python 3.12 --python-preference only-managed `
     --torch-backend=cu130 --force-reinstall

   Linux · NVIDIA

   uv pip install "<PACKAGE_SPECIFIER>==<VERSION>" \
     --python 3.12 --python-preference only-managed \
     --torch-backend=cu130 --force-reinstall

   Windows · Intel Arc

   uv pip install "<PACKAGE_SPECIFIER>==<VERSION>" `
     --python 3.12 --python-preference only-managed `
     --torch-backend=xpu --force-reinstall

   Linux · Intel Arc

   uv pip install "<PACKAGE_SPECIFIER>==<VERSION>" \
     --python 3.12 --python-preference only-managed \
     --torch-backend=xpu --force-reinstall

   Windows · AMD

   Also substitute your GPU’s <TARGET> (see below).

   uv pip install <PACKAGE_SPECIFIER>==<VERSION> `
     "torch[device-<TARGET>]==2.13.0+rocm10.0.0" `
     "torchvision[device-<TARGET>]==0.28.0+rocm10.0.0" `
     --index https://stable.repo.amd.com/rocm/whl-next/ `
     --index-strategy unsafe-best-match `
     --python 3.12 --python-preference only-managed `
     --force-reinstall

   Linux · AMD

   Also substitute your GPU’s <TARGET> (see below).

   uv pip install <PACKAGE_SPECIFIER>==<VERSION> \
     "torch[device-<TARGET>]==2.13.0+rocm10.0.0" \
     "torchvision[device-<TARGET>]==0.28.0+rocm10.0.0" \
     --index https://stable.repo.amd.com/rocm/whl-next/ \
     --index-strategy unsafe-best-match \
     --python 3.12 --python-preference only-managed \
     --force-reinstall

   Windows · ARM64

   uv pip install <PACKAGE_SPECIFIER>==<VERSION> `
     --python cpython-3.12-windows-aarch64-none --python-preference only-managed `
     --index https://pypi.nvidia.com/nvtorch_oot/ `
     --find-links https://github.com/invoke-ai/InvokeAI/releases/download/win-arm64-wheels-v1/index.html `
     --force-reinstall

   Linux · None (CPU)

   On x86_64:

   uv pip install "<PACKAGE_SPECIFIER>==<VERSION>" \
     --python 3.12 --python-preference only-managed \
     --torch-backend=cpu --force-reinstall

   On ARM64 (aarch64), without a torch backend:

   uv pip install <PACKAGE_SPECIFIER>==<VERSION> \
     --python 3.12 --python-preference only-managed \
     --force-reinstall

   Windows · Other / none

   uv pip install <PACKAGE_SPECIFIER>==<VERSION> `
     --python 3.12 --python-preference only-managed `
     --force-reinstall

   macOS

   uv pip install <PACKAGE_SPECIFIER>==<VERSION> \
     --python 3.12 --python-preference only-managed \
     --force-reinstall

   Windows, Linux · AMD

   <TARGET>	GPUs
   gfx1201	RX 9070 series and Radeon AI PRO R9700
   gfx1200	RX 9060 series
   gfx1100	RX 7900 series
   gfx1101	RX 7700 and 7800 series
   gfx1102	RX 7600 series
   gfx1151	Ryzen AI Max

   For other GPUs, see AMD’s GPU target table.

   Linux · AMD

   For a Vega-based card (gfx900/gfx906), install PyTorch’s ROCm 7.2 build instead:

   uv pip install "<PACKAGE_SPECIFIER>==<VERSION>" \
     --python 3.12 --python-preference only-managed \
     --torch-backend=rocm7.2 --force-reinstall

9. Deactivate and reactivate your venv so that the invokeai-specific commands become available in the environment:

   Windows

   deactivate
   .venv\Scripts\activate

   macOS, Linux

   deactivate && source .venv/bin/activate

10. Run the application, specifying the directory you created earlier as the root directory:

    invokeai-web --root ~/invokeai

    To keep an existing install as it is, give v7 a directory of its own: see Run v7 alongside v6.

If you run Invoke on a headless server, you might want to install and run Invoke on the command line.

We do not plan to maintain scripts to do this moving forward, instead focusing our dev resources on the GUI launcher.

You can create your own scripts for this by copying the handful of commands in this guide. uv’s pip interface docs may be useful.