Skip to content

Manual Install#

Warning

Python experience is mandatory.

If you want to use Invoke locally, you should probably use the launcher.

If you want to contribute to Invoke or run the app on the latest dev branch, instead follow the dev environment guide.

InvokeAI is distributed as a python package on PyPI, installable with pip. There are a few things that are handled by the launcher that you'll need to manage manually, described in this guide.

Requirements#

Before you start, go through the installation requirements.

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):

    mkdir ~/invokeai
    cd ~/invokeai
    
    mkdir $Home/invokeai
    cd $Home/invokeai
    
  3. Create a virtual environment in that directory:

    uv venv --relocatable --prompt invoke --python 3.11 --python-preference only-managed .venv
    

    This command creates a portable virtual environment at .venv complete with a portable python 3.11. It doesn't matter if your system has no python installed, or has a different version - uv will handle everything.

  4. Activate the virtual environment:

    source .venv/bin/activate
    
    .venv\Scripts\activate
    
  5. Choose a version to install. Review the GitHub releases page.

  6. Determine the package package specifier to use when installing. This is a performance optimization.

    • If you have an Nvidia 20xx series GPU or older, use invokeai[xformers].
    • If you have an Nvidia 30xx series GPU or newer, or do not have an Nvidia GPU, use invokeai.
  7. Determine the PyPI index URL to use for installation, if any. This is necessary to get the right version of torch installed.

    • If you are on Windows with an Nvidia GPU, use https://download.pytorch.org/whl/cu124.
    • If you are on Linux with no GPU, use https://download.pytorch.org/whl/cpu.
    • If you are on Linux with an AMD GPU, use https://download.pytorch.org/whl/rocm6.1.
    • In all other cases, do not use an index.
    • If you are on Windows with an Nvidia GPU, use https://download.pytorch.org/whl/cu124.
    • If you are on Linux with no GPU, use https://download.pytorch.org/whl/cpu.
    • If you are on Linux with an AMD GPU, use https://download.pytorch.org/whl/rocm5.2.
    • In all other cases, do not use an index.
  8. Install the invokeai package. Substitute the package specifier and version.

    uv pip install <PACKAGE_SPECIFIER>=<VERSION> --python 3.11 --python-preference only-managed --force-reinstall
    

    If you determined you needed to use a PyPI index URL in the previous step, you'll need to add --index=<INDEX_URL> like this:

    uv pip install <PACKAGE_SPECIFIER>=<VERSION> --python 3.11 --python-preference only-managed --index=<INDEX_URL> --force-reinstall
    
  9. Deactivate and reactivate your venv so that the invokeai-specific commands become available in the environment:

    deactivate && source .venv/bin/activate
    
    deactivate
    .venv\Scripts\activate
    
  10. Run the application, specifying the directory you created earlier as the root directory:

    invokeai-web --root ~/invokeai
    
    invokeai-web --root $Home/invokeai
    

Headless Install and Launch Scripts#

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.