How To Install Invoke AI on Windows in 2023

Bill Meeks
19 Nov 202313:32

TLDRThis video tutorial guides professional artists and designers through the process of installing Invoke AI on Windows. The host explains the technical requirements, such as an Nvidia graphics card with sufficient VRAM and at least 12 GB of RAM. The installation process includes downloading the installer from Invoke AI's GitHub page, extracting the files, and running the install.bat file. The video also covers configuring the software with the user's GPU type, selecting a manual configuration, and choosing which models to install. The host demonstrates adding existing stable diffusion models to Invoke AI and testing the software with a creative prompt, showcasing the generated images. The tutorial concludes with an invitation for viewers to follow the creator's journey in building the Everly Heights universe using Invoke AI and to support the project on Patreon for access to custom tools and models.

Takeaways

  • 🎨 **Professional Tool for Artists**: Invoke AI is a generative AI art tool designed for professional artists and designers.
  • ☕ **Coffee Break Tutorial**: The tutorial guides you through installing Invoke AI with a casual, conversational tone.
  • 💻 **Technical Requirements**: To run Invoke AI on Windows, you need an Nvidia graphics card with at least 4 GB of VRAM (8 GB for the latest version of stable diffusion), 12 GB of RAM, and 18 GB of free hard drive space.
  • 🐍 **Python Version**: Ensure you have Python version 3.10 or 3.11 installed, and add Python to the system path during installation.
  • 📚 **Microsoft Visual C++ Redistributable**: Install the Microsoft Visual C++ redistributable from 2015 to 2022 if not already present.
  • 📥 **Download and Install**: Visit Invoke AI's GitHub page to download the installer and follow the automated installation process.
  • 📂 **Custom Installation Path**: You can choose a custom installation path to avoid using the default location.
  • 💡 **GPU Selection**: Select the type of GPU you have during the installation, with the process tailored for Nvidia GPUs.
  • 🔄 **Automatic Configuration**: Invoke AI offers an automatic configuration option to get the base models, or you can perform a manual configuration.
  • 🔍 **Model Manager**: After installation, use the Model Manager to import existing stable diffusion models into Invoke AI.
  • 🖼️ **Image Generation**: Test the installation by generating images with prompts, showcasing the tool's capabilities.
  • 🌐 **Web Interface**: Invoke AI can be launched in a browser-based interface for ease of use.

Q & A

  • What is Invoke AI and what does it offer to professional artists and designers?

    -Invoke AI is a generative AI art tool designed for professional artists and designers. It combines the power of stable diffusion with professional workflows and a clean, intuitive, and elegant user interface to facilitate creative processes with minimal effort and maximum power.

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

    -To run Invoke AI on Windows, you need 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 (preferably more), and the correct version of Python installed (at least 3.10 or 3.11).

  • Why is Invoke AI not compatible with AMD graphics cards on Windows?

    -The script does not provide a specific reason for the incompatibility with AMD graphics cards on Windows. However, it mentions that Invoke AI can be run on Linux with AMD cards, indicating that the issue might be related to the specific configuration or support for Nvidia GPUs in the Windows version of the software.

  • How can one check their current Python version and install a compatible version if needed?

    -To check the current Python version, open the command prompt by typing 'CMD' in the Start menu, then type 'python --version'. If the correct version is not installed, you can download it from python.org/downloads. During installation, ensure to check the box that says 'Add Python to PATH' to avoid extra setting manipulation for Invoke AI.

  • What is the role of the Microsoft Visual C++ Redistributable in the Invoke AI installation process?

    -The Microsoft Visual C++ Redistributable from 2015 to 2022 is required for the Invoke AI installation. If these libraries are not already installed on your system, you will need to install them. The installer for these libraries can be found in the description provided with the Invoke AI installation guide.

  • How does the automated installer for Invoke AI work?

    -The automated installer for Invoke AI is downloaded from the Invoke AI GitHub page. After downloading, the installer is extracted and run. The installation process involves several steps, including extracting the installer, running the 'install.bat' file, and following the prompts to set up the program, including selecting the GPU type and installing models.

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

    -After installing Invoke AI, you can add existing stable diffusion models by going to the model manager within the program, selecting 'import models', and providing the path to where your models are stored. The program will then import the models, making them available for use within Invoke AI.

  • How does Invoke AI handle the installation of upscaling models?

    -Invoke AI will prompt the user to download some upscaling models during the installation process. If the user already has these models, they can choose to link them up instead of downloading. The user can select the models they want to install and apply the changes to complete the installation.

  • What is the purpose of the 'creativeml responsible AI license' mentioned in the script?

    -The 'creativeml responsible AI license' is a license agreement that users need to accept during the installation process. While the script does not provide specific details about the license, it suggests that it is a standard practice to ensure responsible use of AI technologies.

  • How can users launch the Invoke AI interface after installation?

    -After installation, users can launch the Invoke AI interface by navigating to the folder where Invoke AI is installed and double-clicking on the 'invoke.bat' file. They will then be prompted to choose an option, and selecting the option to run the browser-based interface will launch Invoke AI in the user's web browser.

  • What kind of creative output can be expected from using Invoke AI with stable diffusion models?

    -Invoke AI with stable diffusion models can generate a wide range of creative outputs. For example, the script demonstrates generating images of Superman drinking beer in a bar using a 1.5 model, resulting in four different variations of the scene.

Outlines

00:00

🚀 Introduction to Invoke AI for Creative Professionals

The video begins with an introduction to Invoke AI, a generative AI tool that combines the power of stable diffusion with professional workflows and a user-friendly interface. The host, presumably a professional artist or designer, offers to guide viewers through the installation process of Invoke AI on Windows. The video is sponsored by Patreon, and viewers are encouraged to support the project for access to custom tools and models. The host also mentions his recent sitcom 'Very Special' and his conversation with Invoke AI's founder, Kent Kiry. Before diving into the installation, the host outlines the technical requirements, which include an Nvidia graphics card with sufficient VRAM, a specific amount of RAM and hard drive space, and the correct version of Python. The video provides instructions on how to check and install these prerequisites.

05:05

📥 Installing Invoke AI and Setting Up the Environment

The host proceeds to guide viewers through the installation of Invoke AI. They start by downloading the installer from the Invoke AI GitHub page and extracting it to a chosen folder. The installation process involves running an 'install.bat' file and following the on-screen instructions, which include enabling long path support and setting up the Windows registry. The host also discusses the need for the Microsoft Visual C++ Redistributable and provides a link for download. After ensuring that all requirements are met, the host demonstrates how to select the GPU type, choose the installation location, and opt for manual configuration. This involves downloading models from Huggingface, which requires a token, and selecting the desired models for installation. The host chooses to install only the base models initially and plans to add custom models later.

10:08

🖼️ Exploring Invoke AI's Interface and Testing with a Prompt

Once Invoke AI is installed, the host shows how to run the browser-based interface and access the program. They note the absence of models in the interface, which is expected since the host has additional models installed on their system. The host guides viewers on how to import existing models into Invoke AI using the model manager. After importing the models, the host tests the tool by generating images based on a prompt: 'Superman drinking beer at a bar.' They use a 1.5 model and set the image parameters to create four different images. The video concludes with a demonstration of the image generation process and the results, showcasing Invoke AI's capabilities. The host also invites viewers to request in-depth tutorials on using Invoke AI and to follow their creative journey on various social media platforms and Patreon.

Mindmap

Keywords

💡Invoke 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 an intuitive user interface. In the video, the host demonstrates how to install Invoke AI on Windows and explores its features, emphasizing its ease of use and power for creative tasks.

💡Stable 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 with minimal effort. The video mentions different versions of stable diffusion, including sdxl, which is the latest version requiring more VRAM.

💡Nvidia Graphics Card

An Nvidia graphics card is a specific type of hardware required to run Invoke AI, particularly for handling the graphics-intensive tasks associated with AI image generation. The video specifies that Invoke AI requires an Nvidia-based graphics card with at least 4 GB of VRAM for basic operations or 8 GB for the latest stable diffusion models.

💡VRAM

VRAM, or Video RAM, is the memory used by graphics cards to store image data. The amount of VRAM is crucial for running graphics-intensive applications like Invoke AI, as it determines the resolution and complexity of images that can be processed. The video mentions the need for at least 4 GB of VRAM for basic stable diffusion models.

💡Python

Python is a programming language that is often used for developing and running AI applications. Invoke AI requires a specific version of Python (3.10 or 3.11) to function correctly. The video provides instructions on how to check the Python version and where to download the required version if it's not already installed.

💡Microsoft 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 mentions the necessity of having this component installed from 2015 to 2022 versions for Invoke AI to function.

💡RAM

RAM, or Random Access Memory, is the main memory that a computer uses to store data temporarily while it's being processed. The video specifies a requirement of at least 12 GB of RAM for running Invoke AI, which is essential for handling the large amounts of data used in AI image generation.

💡Hard Drive Space

Hard drive space refers to the amount of storage available on a computer's hard drive. The video mentions the need for at least 18 gigabytes of free hard drive space for installing Invoke AI and its models, with a recommendation for more space if additional models are to be downloaded.

💡Huggingface Token

A Huggingface token is used to access models and services on the Huggingface platform, which hosts a variety of AI models. In the context of the video, the token is required if the user chooses to download models from Huggingface during the Invoke AI setup process.

💡CUDA

CUDA is a parallel computing platform and programming model developed by Nvidia that allows software developers to use Nvidia GPUs for general purpose processing. The video indicates that Invoke AI requires an Nvidia GPU that supports CUDA for optimal performance.

💡Auto Configuration

Auto Configuration in the context of the video refers to the automated setup process of Invoke AI, which includes downloading base models and setting up the environment. The host chooses manual configuration to sync with existing installations and customize the setup according to personal preferences.

Highlights

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

Invoke AI combines the power of stable diffusion with professional workflows and an intuitive user interface.

Technical requirements for running Invoke on Windows include an Nvidia-based graphics card with at least 4 GB of VRAM.

At least 12 GB of RAM and 18 GB of free hard drive space are recommended for optimal performance.

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 offers an automated installer for ease of setup.

The installation process includes configuring the GPU type and selecting an installation location.

Users can choose between an automatic configuration with base models or a manual configuration.

A huggingface token is required if opting to download models from huggingface.

Custom models can be added to Invoke AI through the model manager after installation.

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

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

The process of adding custom models and using Invoke AI for creative projects is detailed in the tutorial.

The founder of Invoke AI, Kent Kiry, discusses the tool's capabilities in an interview available on YouTube and as a podcast episode.

The tutorial encourages viewers to provide feedback on whether they would like to see in-depth tutorials using Invoke AI.

Support for the project and access to custom tools and models can be obtained through Patreon support.

The Everly Heights Universe is being built using technology like Invoke AI, and supporters can access behind-the-scenes content.