How To Install Invoke AI on Windows in 2023

Bill Meeks
19 Nov 202313:32

TLDRThe video provides a step-by-step guide on installing Invoke AI on Windows for professional artists and designers. It covers the technical requirements, including an Nvidia graphics card with sufficient VRAM, at least 12 GB of RAM, and specific Python versions. The tutorial explains how to download the installer from GitHub, extract it, and run the installation process. It also guides viewers on adding custom stable diffusion models to Invoke AI and briefly explores the program's features. The host demonstrates generating images using the software, showcasing its capabilities with a creative example of Superman drinking beer. The video concludes with an invitation for viewers to follow the creator's journey in building the Everly Heights universe using Invoke AI.

Takeaways

  • ๐ŸŽจ **Professional AI Tool**: Invoke AI is a generative AI art tool designed for professional artists and designers.
  • โ˜• **Effortless Installation**: The tutorial provides a step-by-step guide on how to install Invoke AI on Windows.
  • ๐Ÿ’ป **Technical Requirements**: To run Invoke AI, you need an Nvidia graphics card with at least 4 GB of VRAM, 12 GB of RAM, and 18 GB of free hard drive space.
  • ๐Ÿ **Python Version**: Ensure you have Python version 3.10 or 3.11 installed, and add Python to the system path during installation.
  • ๐Ÿ“‹ **Microsoft Visual C++ Redistributable**: Install the Microsoft Visual C++ redistributable from 2015 to 2022 if not already present.
  • ๐Ÿ“ฅ **Downloading Invoke AI**: Visit the Invoke AI GitHub page to download the latest version of the automated installer.
  • ๐Ÿ“‚ **Installation Folder**: Choose a suitable folder for installation, preferably outside the main drive to save space.
  • ๐Ÿ”ง **GPU Selection**: Select the type of GPU you have, with the tutorial focusing on Nvidia GPUs that support CUDA.
  • ๐Ÿ”„ **Automatic Configuration**: Invoke AI offers an automatic configuration option to get the base models, but a manual configuration is also possible.
  • ๐Ÿ” **Adding Models**: After installation, you can add existing stable diffusion models to Invoke AI through the model manager.
  • ๐Ÿ–ผ๏ธ **Testing the Tool**: Test the installation by generating images with different prompts to ensure everything is working correctly.
  • ๐ŸŒ **Web Interface**: Invoke AI can be launched in a browser-based interface for ease of use.

Q & A

  • What is the purpose of the video?

    -The purpose of the video is to guide professional artists and designers through the process of installing Invoke AI on Windows, a generative AI art tool that combines the power of stable diffusion with professional workflows and a clean, intuitive UI.

  • What are the minimum technical requirements to run Invoke on Windows?

    -The minimum technical requirements include an Nvidia-based graphics card with at least 4 GB of VRAM (8 GB for the latest version of stable diffusion called sdxl), at least 12 GB of RAM, at least 18 GB of free hard drive space, and the correct version of Python (3.10 or 3.11).

  • Why is an Nvidia graphics card necessary for Invoke AI?

    -Invoke AI requires an Nvidia graphics card because it supports CUDA, which is necessary for running the stable diffusion models that Invoke AI uses. AMD cards are not supported on Windows for this tool.

  • How can one check the installed version of Python on their system?

    -To check the installed version of Python, one can open the command prompt by typing 'CMD' in the start menu, then type 'python --version' to see the current version.

  • What is the role of Microsoft Visual C++ redistributable in the installation process?

    -The Microsoft Visual C++ redistributable is a set of libraries that may be required for Invoke AI to function properly. If not already installed, the user needs to download and install it from the provided link.

  • How does the automated installer for Invoke AI work?

    -The automated installer can be downloaded from the Invoke AI GitHub page. After extraction, the user runs the installer, which guides them through the installation process, including selecting the GPU type, choosing the installation location, and setting up the program.

  • What is the process for adding existing stable diffusion models to Invoke AI?

    -After installation, the user can add existing models by going to the model manager within Invoke AI, selecting 'import models', and providing the path to where the models are stored.

  • How does Invoke AI help in creating the Everly Heights universe?

    -Invoke AI is used as a tool to create art and designs for the Everly Heights universe, a sitcom. The video's presenter uses the tool to build the first cartoon set of the universe, showcasing the capabilities of Invoke AI in professional creative work.

  • What is the process for configuring Invoke AI for the first time?

    -During the first run, Invoke AI prompts the user to choose between an automatic configuration (which downloads base models) or a manual configuration. The user can also specify the folder for saving images, link up custom models, and accept the responsible AI license.

  • What are the steps to run Invoke AI after installation?

    -After installation, the user navigates to the installation folder and double-clicks on 'invoke.bat'. They then select the option to run the browser-based interface and click the provided link to launch Invoke AI in the browser.

  • How can one get access to custom tools and stable diffusion models used in building Everly Heights?

    -Supporting the project on Patreon can grant access to custom tools and stable diffusion models used to build Everly Heights. This support also provides additional benefits like a production diary.

  • What is the presenter's recommendation for the hard drive space for Invoke AI?

    -While the minimum requirement is 18 GB of free hard drive space, the presenter recommends having at least twice that amount to accommodate the space needed for downloading models and setting up the program.

Outlines

00:00

๐Ÿš€ Getting Started with Invoke AI: Installation and Setup

This paragraph introduces the viewer to the process of installing Invoke AI, a generative AI tool that integrates with stable diffusion for professional artists and designers. The host outlines the necessity of having an Nvidia graphics card with sufficient VRAM, at least 12 GB of RAM, and 18 GB of free hard drive space. The viewer is also informed about the required Python version (3.10 or 3.11) and the Microsoft Visual C++ redistributable. Detailed steps are provided for downloading the installer from GitHub, extracting it, and initiating the installation process, including configuring the Windows registry and setting up the program's directory.

05:05

๐Ÿ“š Customizing Invoke AI: Selecting GPU and Models

The second paragraph delves into the customization process of Invoke AI, starting with the selection of the GPU type, specifically focusing on Nvidia GPUs that support CUDA. The host chooses to install the software in a non-default folder to keep AI programs separate from the main drive. The viewer is guided through the manual configuration, including obtaining a huggingface token for model downloads and deciding on the installation of various models and features. The host opts for a manual approach to sync with an existing setup and emphasizes the ability to customize and link up models post-installation.

10:08

๐Ÿ–ผ๏ธ Using Invoke AI: Running the Interface and Testing Models

The final paragraph demonstrates how to run Invoke AI after installation. The host explains how to launch the browser-based interface and access the model manager to import existing models into the system. Despite encountering some issues with a few models, the process is generally smooth. To verify that everything is functioning correctly, the host uses Invoke AI to generate images based on a creative prompt (Superman drinking beer) with the stable diffusion 1.5 model. The paragraph concludes with an invitation for viewers to engage with the content, suggesting potential future tutorials and interviews, and providing information on how to follow and support the project.

Mindmap

Keywords

๐Ÿ’กInvoke AI

Invoke AI is a generative AI art tool designed for professional artists and designers. It combines the capabilities of stable diffusion with professional workflows and a user-friendly interface. In the video, the host demonstrates how to install Invoke AI on Windows and explores its features, emphasizing its utility for creating art with minimal effort but maximum power.

๐Ÿ’กStable Diffusion

Stable Diffusion is a type of generative AI model used for creating images from textual descriptions. It is a core component of Invoke AI, allowing users to generate professional-grade artwork. The video mentions different versions of stable diffusion, including sdxl, which is the latest version requiring more VRAM.

๐Ÿ’กNvidia Graphics Card

An Nvidia graphics card is a specific type of hardware required to run Invoke AI, particularly for handling the graphical processing demands of stable diffusion models. The video specifies that at least 4 GB of VRAM is needed, or 8 GB for the latest version of stable diffusion.

๐Ÿ’กVRAM

VRAM, or Video Random Access Memory, is the memory used by graphics cards to store image data for rendering images, videos, and 3D models. The script mentions that for Invoke AI, a minimum of 4 GB VRAM is required, with 8 GB recommended for the most advanced features.

๐Ÿ’กPython

Python is a programming language that is essential for running Invoke AI. The video specifies that a version of Python 3.10 or higher is needed. It is used for executing the scripts that power the AI's functionalities.

๐Ÿ’กMicrosoft Visual C++ Redistributable

The Microsoft Visual C++ Redistributable is a set of runtime components that are required for some applications, including Invoke AI, to run properly on Windows. The video instructs viewers to install this if they do not already have it.

๐Ÿ’กInstallation Process

The installation process for Invoke AI involves downloading the installer from GitHub, extracting it, and following a series of steps to set up the program. This includes configuring the system for the type of GPU, selecting the installation folder, and choosing which models to install.

๐Ÿ’กHuggingface Token

A Huggingface token is used to access models on the Huggingface platform, which can be integrated with Invoke AI. The video shows how to obtain a token from Huggingface's website and use it during the installation process to download models.

๐Ÿ’กModel Manager

The Model Manager is a feature within Invoke AI that allows users to import and manage their AI models. The video demonstrates how to use the Model Manager to add existing stable diffusion models to Invoke AI.

๐Ÿ’กCreative ML Responsible AI License

This license is an agreement that users must accept during the installation process, indicating their commitment to using AI responsibly. The video mentions accepting this license as part of the setup.

๐Ÿ’กBrowser-Based Interface

Invoke AI features a browser-based interface, which means it can be accessed and used through a web browser. The video shows how to launch Invoke AI in the browser after the installation is complete.

Highlights

The tutorial provides a step-by-step guide on installing Invoke AI on Windows for professional artists and designers.

Invoke AI combines the power of stable diffusion with professional workflows and a clean, intuitive UI.

Technical requirements include an Nvidia-based graphics card with at least 4 GB of VRAM and 12 GB of RAM.

For the latest version of stable diffusion (sdxl), 8 GB of VRAM is recommended.

AMD card users can run Invoke on Linux but not on Windows.

At least 18 GB of free hard drive space is needed, with a recommendation for more after downloading models.

Python version 3.10 or 3.11 is required, with instructions provided for checking and updating if necessary.

The Microsoft Visual C++ redistributable from 2015 to 2022 must be installed if not already present.

Invoke AI's GitHub page provides an automated installer for Windows users.

The installation process includes an option for manual configuration to sync with existing stable diffusion models.

Users can choose to download models from huggingface if desired, requiring a huggingface token.

The installation allows for selecting the type of GPU and offers options for automatic or manual configuration.

After installation, users can add custom models through the model manager in Invoke AI.

Invoke AI provides a browser-based interface for ease of use.

The tutorial demonstrates creating an image of Superman drinking beer using Invoke AI's 1.5 model.

The process showcases the ability to generate multiple variations of an image with different settings.

The founder of Invoke AI, Kent Kiry, is interviewed for further insights into the tool.

The tutorial concludes with an invitation for feedback on in-depth tutorials and further exploration of the tool.