Repository files navigation

InvokeAI is a leading creative engine built to empower professionalsand enthusiasts alike. Generate and create stunning visual media usingthe latest AI-driven technologies. InvokeAI offers an industry leadingWeb Interface, interactive Command Line Interface, and also serves asthe foundation for multiple commercial products.

Quick links: [How toInstall] [Discord Server] [Documentation andTutorials] [Code andDownloads] [Bug Reports][Discussion,Ideas & Q&A]

Table of Contents 📝

Getting Started

1. 🏁Quick Start
2. 🖥️Hardware Requirements

More About Invoke

1. 🌟Features
2. 📣Latest Changes
3. 🛠️Troubleshooting

Supporting the Project

1. 🤝Contributing
2. 👥Contributors
3. 💕Support

For full installation and upgrade instructions, please see:InvokeAI Installation Overview

If upgrading from version 2.3, please readMigrating a 2.3 rootdirectory to 3.0 first.

1. Go to the bottom of theLatest Release Page

2. Download the .zip file for your OS (Windows/macOS/Linux).

3. Unzip the file.

4. Windows: double-click on theinstall.bat script.macOS: Open a Terminal window, drag the fileinstall.sh from Finderinto the Terminal, and press return.Linux: runinstall.sh.

5. You'll be asked to confirm the location of the folder in whichto install InvokeAI and its image generation model files. Pick alocation with at least 15 GB of free memory. More if you plan oninstalling lots of models.

6. Wait while the installer does its thing. After installing the software,the installer will launch a script that lets you configure InvokeAI andselect a set of starting image generation models.

7. Find the folder that InvokeAI was installed into (it is not thesame as the unpacked zip file directory!) The default location of thisfolder (if you didn't change it in step 5) is~/invokeai onLinux/Mac systems, andC:\Users\YourName\invokeai on Windows. This directory will contain launcher scripts namedinvoke.sh andinvoke.bat.

8. On Windows systems, double-click on theinvoke.bat file. OnmacOS, open a Terminal window, draginvoke.sh from the folder intothe Terminal, and press return. On Linux, runinvoke.sh

9. Press 2 to open the "browser-based UI", press enter/return, wait aminute or two for Stable Diffusion to start up, then open your browserand go tohttp://localhost:9090.

10. Typebanana sushi in the box on the top left and clickInvoke

You must have Python 3.9 through 3.11 installed on your machine. Earlier orlater versions are not supported.Node.js also needs to be installed along with yarn (can be installed withthe commandnpm install -g yarn if needed)

1. Open a command-line window on your machine. The PowerShell is recommended for Windows.

2. Create a directory to install InvokeAI into. You'll need at least 15 GB of free space:

   mkdir invokeai

3. Create a virtual environment named.venv inside this directory and activate it:

   cd invokeaipython -m venv .venv --prompt InvokeAI

4. Activate the virtual environment (do it every time you run InvokeAI)

   For Linux/Mac users:

   source .venv/bin/activate

   For Windows users:

   .venv\Scripts\activate

5. Install the InvokeAI module and its dependencies. Choose the command suited for your platform & GPU.

   For Windows/Linux with an NVIDIA GPU:

   pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117

   For Linux with an AMD GPU:

   pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2

   For non-GPU systems:

   pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu

   For Macintoshes, either Intel or M1/M2:

   pip install InvokeAI --use-pep517

6. Configure InvokeAI and install a starting set of image generation models (you only need to do this once):

   invokeai-configure

7. Launch the web server (do it every time you run InvokeAI):

   invokeai-web

8. Build Node.js assets

cd invokeai/frontend/web/yarn vite build

9. Point your browser tohttp://localhost:9090 to bring up the web interface.
10. Typebanana sushi in the box on the top left and clickInvoke.

Be sure to activate the virtual environment each time before re-launching InvokeAI,usingsource .venv/bin/activate or.venv\Scripts\activate.

This fork is supported across Linux, Windows and Macintosh. Linuxusers can use either an Nvidia-based card (with CUDA support) or anAMD card (using the ROCm driver). For full installation and upgradeinstructions, please see:InvokeAI Installation Overview

The InvokeAI root directory is where the InvokeAI startup file,installed models, and generated images are stored. It is ordinarilynamedinvokeai and located in your home directory. The contents andlayout of this directory has changed between versions 2.3 and 3.0 andcannot be used directly.

We currently recommend that you use the installer to create a new rootdirectory named differently from the 2.3 one, e.g.invokeai-3 andthen use a migration script to copy your 2.3 models into the newlocation. However, if you choose, you can upgrade this directory inplace. This section gives both recipes.

This is the safer recipe because it leaves your old root directory inplace to fall back on.

1. Follow the instructions above to create and install InvokeAI in adirectory that has a different name from the 2.3 invokeai directory.In this example, we will use "invokeai-3"

2. When you are prompted to select models to install, select a minimalset of models, such as stable-diffusion-v1.5 only.

3. After installation is complete launchinvokeai.sh (Linux/Mac) orinvokeai.bat and select option 8 "Open the developers console". Thiswill take you to the command line.

4. Issue the commandinvokeai-migrate3 --from /path/to/v2.3-root --to /path/to/invokeai-3-root. Provide the correct--from and--topaths for your v2.3 and v3.0 root directories respectively.

This will copy and convert your old models from 2.3 format to 3.0format and create a newmodels directory in the 3.0 directory. Theold models directory (which contains the models selected at installtime) will be renamedmodels.orig and can be deleted once you haveconfirmed that the migration was successful.

If you wish, you can pass the 2.3 root directory to both--from and--to in order to update in place. Warning: this directory will nolonger be usable with InvokeAI 2.3.

For the adventurous, you may do an in-place upgrade from 2.3 to 3.0without touching the command line. *This recipe does not work onWindows platforms due to a bug in the Windows version of the 2.3upgrade script. See the next section for a Windows recipe.

1. Launch the InvokeAI launcher script in your current v2.3 root directory.

2. Select option [9] "Update InvokeAI" to bring up the updater dialog.

3. Select option [1] to upgrade to the latest release.

4. Once the upgrade is finished you will be returned to the launchermenu. Select option [7] "Re-run the configure script to fix a brokeninstall or to complete a major upgrade".

This will run the configure script against the v2.3 directory andupdate it to the 3.0 format. The following files will be replaced:

• The invokeai.init file, replaced by invokeai.yaml
• The models directory
• The configs/models.yaml model index

The original versions of these files will be saved with the suffix".orig" appended to the end. Once you have confirmed that the upgradeworked, you can safely remove these files. Alternatively you canrestore a working v2.3 directory by removing the new files andrestoring the ".orig" files' original names.

Windows Users can upgrade with the

1. Enter the 2.3 root directory you wish to upgrade
2. Launchinvoke.sh orinvoke.bat
3. Select the "Developer's console" option [8]
4. Type the following commands

pip install "invokeai @ https://github.com/invoke-ai/InvokeAI/archive/refs/tags/v3.0.0" --use-pep517 --upgradeinvokeai-configure --root .

(Replacev3.0.0 with the current release number if this document is out of date).

The first command will install and upgrade new software to runInvokeAI. The second will prepare the 2.3 directory for use with 3.0.You may now launch the WebUI in the usual way, by selecting option [1]from the launcher script

The migration script will migrate your invokeai settings and models,including textual inversion models, LoRAs and merges that you may haveinstalled previously. However it doesnot migrate the generatedimages stored in your 2.3-format outputs directory. You will need tomanually import selected images into the 3.0 gallery via drag-and-drop.

InvokeAI is supported across Linux, Windows and macOS. Linuxusers can use either an Nvidia-based card (with CUDA support) or anAMD card (using the ROCm driver).

You will need one of the following:

• An NVIDIA-based graphics card with 4 GB or more VRAM memory. 6-8 GBof VRAM is highly recommended for rendering using the StableDiffusion XL models
• An Apple computer with an M1 chip.
• An AMD-based graphics card with 4GB or more VRAM memory (Linuxonly), 6-8 GB for XL rendering.

We do not recommend the GTX 1650 or 1660 series video cards. They areunable to run in half-precision mode and do not have sufficient VRAMto render 512x512 images.

Memory - At least 12 GB Main Memory RAM.

Disk - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.

Feature documentation can be reviewed by navigating tothe InvokeAI Documentation page

InvokeAI offers a locally hosted Web Server & React Frontend, with an industry leading user experience. The Web-based UI allows for simple and intuitive workflows, and is responsive for use on mobile devices and tablets accessing the web server.

The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/outpainting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.

Invoke AI's backend is built on a graph-based execution architecture. This allows for customizable generation pipelines to be developed by professional users looking to create specific workflows to support their production use-cases, and will be extended in the future with additional capabilities.

Invoke AI provides an organized gallery system for easily storing, accessing, and remixing your content in the Invoke workspace. Images can be dragged/dropped onto any Image-base UI element in the application, and rich metadata within the Image allows for easy recall of key prompts or settings used in your workflow.

• Support for both ckpt and diffusers models
• SD 2.0, 2.1, XL support
• Upscaling Tools
• Embedding Manager & Support
• Model Manager & Support
• Node-Based Architecture
• Node-Based Plug-&-Play UI (Beta)

For our latest changes, view ourReleaseNotes and theCHANGELOG.

Please check out ourQ&A to get solutions for common installationproblems and other issues.

Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, codecleanup, testing, or code reviews, is very much encouraged to do so.

To join, just raise your hand on the InvokeAI Discord server (#dev-chat) or the GitHub discussion board.

If you'd like to help with translation, please see ourtranslation guide.

If you are unfamiliar with howto contribute to GitHub projects, here is aGetting Started Guide. A full set of contribution guidelines, along with templates, are in progress. You canmake your pull request against the "main" branch.

We hope you enjoy using our software as much as we enjoy creating it,and we hope that some of those of you who are reading this will electto become part of our community.

Welcome to InvokeAI!

This fork is a combined effort of various people from across the world.Check out the list of all these amazing people. We thank them fortheir time, hard work and effort.

For support, please use this repository's GitHub Issues tracking service, or join the Discord.

Original portions of the software are Copyright (c) 2023 by respective contributors.