This One Simple Plugin Adds Realtime AI Assistance to Krita

Nerdy Rodent
24 Nov 202314:31

TLDRDiscover how to integrate real-time AI assistance into Krita with a simple plugin. The tutorial guides users through installing and setting up the plugin, leveraging the power of Creer and Comfy UI for almost instantaneous artwork creation. Learn about the system requirements, the installation process, and how to customize settings for an optimal experience. The video also demonstrates the plugin's capabilities, including live drawing and image generation, showcasing its potential to enhance artistic creativity and efficiency.


  • 🎨 The video introduces a plugin that enhances Krita with realtime AI assistance for drawing.
  • 🐦 In two simple steps, anyone can draw an owl using the plugin's assistance.
  • 🚀 The plugin utilizes live stable diffusion to create masterpieces in near real-time.
  • 🖌️ Users benefit from various brushes and tools similar to other painting applications.
  • 📈 The plugin is built on LCM, making it compatible with Comfy UI for an enhanced experience.
  • 💻 System requirements for stable diffusion include a minimum of 6GB VRAM and OS support for Linux or Windows, with experimental Mac support.
  • 🔧 Installation of the plugin involves downloading it from GitHub and unzipping it into the resources folder of the Creer application.
  • 🔄 After installation, users need to enable the plugin through the Python Plugin Manager in Creer's settings.
  • 🌐 Connection to stable diffusion can be managed either locally by the plugin or by connecting to an external server.
  • 🎮 The plugin allows for real-time adjustments and additions to drawings, including control over character poses and image generation.
  • 🎭 The video concludes by suggesting a follow-up tutorial on integrating existing images into stable diffusion art.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is the introduction and setup of a plugin that adds realtime AI assistance to Krita, specifically for creating images using stable diffusion through the power of Creer and a comfortable UI (comfy UI).

  • What are the two steps mentioned in the video to draw an owl?

    -The two steps mentioned are: step one, draw some circles to form the basic shape of the owl, and step two, draw the rest of the details to complete the owl drawing.

  • What does LCM stand for in the context of the video?

    -LCM in the video stands for Lura Creer Manager, which is a part of the system that allows for the management of resources and plugins within the Creer environment.

  • What are the minimum system requirements to run stable diffusion?

    -The minimum system requirements to run stable diffusion are 6 gigabytes of VRAM and an operating system such as Linux or Microsoft Windows, with experimental support for macOS.

  • How can one install Creer?

    -Creer can be installed via a single click in the free software store on Linux or through the Creer website.

  • What is the recommended version of Creer for the plugin?

    -The recommended version of Creer for the plugin is 5.2.1, as mentioned in the video.

  • Where should the downloaded plugin be unzipped?

    -The plugin should be unzipped into the resources folder of the Creer directory.

  • How does one enable the AI image diffusion plugin?

    -To enable the plugin, go to the settings, find the Python plugin manager, tick the box for AI image diffusion, and restart Creer.

  • What is the default option for the local server in the plugin settings?

    -The default option for the local server is to have it managed by the plugin, which also handles the download of necessary resources and models.

  • What are the required custom nodes for the plugin to work properly?

    -The required custom nodes are control net, pre-processors, IP adapter, ultimate SD upscale, and external tooling nodes.

  • How can one troubleshoot issues with the plugin not finding models?

    -One can troubleshoot by checking the client.log and server.log files for any errors, ensuring that the model file names match the expected patterns and that hidden files are shown in the directory view.

  • What is the purpose of the strength bar in the live mode of the plugin?

    -The strength bar adjusts the level of AI assistance in the drawing process, with lower values giving a more cartoony and sketchy feel, and higher values making the image more photographic and realistic.



🎨 Setting Up for Art Creation with Stable Diffusion

This paragraph introduces the process of setting up a computer to create digital art using Stable Diffusion, a powerful image generation tool. It emphasizes the minimal system requirements, such as 6GB of VRAM, and compatibility with Linux, Microsoft Windows, and experimental support for Mac OS. The paragraph explains the need for Creer, a painting app, and its installation process, as well as the recommended version. It also outlines the steps to configure the Creer settings, including locating the resources folder and installing a plugin from GitHub. The paragraph concludes with the initial steps to generate images in real time, highlighting the importance of having the correct setup for a seamless experience.


🔧 Installation and Configuration of Optional Components

The second paragraph delves into the optional components and customizations for the Stable Diffusion setup. It discusses the installation of required custom nodes and models for the 1.7.1 version, including control net pre-processors, IP adapter, ultimate SD upscaler, and external tooling nodes. The paragraph provides troubleshooting tips for issues related to model detection, such as enabling the display of hidden files and checking log files for errors. It also covers the configuration of the server to connect to either a local server managed by the plugin or an external server, with detailed instructions for both options. The paragraph concludes by exploring additional features in the Stable Diffusion menu, such as changing models, prompts, and adjusting interface and performance settings.


🖌️ Real-Time Drawing and Art Generation with Stable Diffusion

The final paragraph focuses on the practical application of Stable Diffusion for real-time drawing and art generation. It describes the process of adjusting brush size and using the denoising strength bar to refine the generated image. The paragraph highlights the ability to add elements such as hats and poses to the artwork, as well as the option to use control nets in real time. It also touches on the possibility of free-form scribbling without prompts and the interpretation of these sketches by the software. The paragraph concludes by discussing the option to copy and modify the generated image, such as changing eye color or refining details, and emphasizes the fun and creative potential of the Stable Diffusion tool.




Krita is a free and open-source digital painting application designed primarily for artists. It offers a wide range of brushes, layer management, and color selection tools, enabling users to create digital art and illustrations. In the context of the video, Krita is the platform where the AI assistance is being added through a plugin, enhancing its capabilities for real-time drawing and image generation.

💡Realtime AI Assistance

Realtime AI Assistance refers to the use of artificial intelligence algorithms to provide immediate support or enhancements to a user's actions. In the video, this concept is applied to the field of digital art, where AI helps in generating images and assisting with the drawing process in real-time, as the user creates their artwork.


Crater, in the context of the video, appears to be a software or plugin that integrates AI capabilities into Krita. It is designed to work with Comfy UI, another tool mentioned in the script, to provide a seamless experience for creating digital art. Crater likely facilitates the real-time AI assistance that the video discusses.

💡Comfy UI

Comfy UI seems to be a user interface extension or a collection of tools that enhance the usability and functionality of Krita. It is mentioned as a prerequisite for using the AI assistance plugin in Krita. Comfy UI likely adds additional features and improvements to the default Krita interface, making it more intuitive and feature-rich for artists.

💡Stable Diffusion

Stable Diffusion is a type of AI model used for generating images from textual descriptions. It is a part of the AI assistance in Krita, which allows users to create complex visual content by simply inputting prompts or descriptions. The video suggests that Stable Diffusion is integrated into Krita through the plugin, enabling users to generate images almost in real-time as they draw.


LCM, or Least Common Multiple, is a mathematical concept that refers to the smallest multiple that is exactly divisible by two or more numbers. In the context of the video, it's not explicitly defined, but it seems to be a component or feature of the AI assistance plugin that helps in the seamless integration of the AI model with Krita's existing functionalities.


VRAM stands for Video RAM, which is a type of memory used to store image data for the graphics processing unit (GPU). In the video, it is mentioned as a system requirement for running Stable Diffusion, indicating that a certain amount of VRAM (6 gigabytes) is necessary to ensure smooth operation of the AI image generation process in Krita.


Dockers, in the context of the video, refers to a user interface element in Krita that provides access to various tools and features. It is mentioned as something that needs to be enabled and is part of the setup process for the AI image generation plugin. Dockers likely serve as a way to access and manage different aspects of the AI assistance within Krita.

💡Python Plugin Manager

Python Plugin Manager is a tool within Krita that allows users to manage Python-based plugins. In the video, it is used to enable the AI image diffusion plugin, which is essential for the real-time AI assistance feature. This manager likely provides an interface for users to install, update, or disable plugins that extend Krita's functionality.

💡Control Nets

Control Nets are a concept related to AI image generation, particularly in the context of Stable Diffusion. They are used to guide the AI in generating images according to specific parameters or constraints. In the video, Control Nets are mentioned as a tool that can be used in real-time while drawing, allowing the user to influence the AI's output based on their preferences or requirements.

💡Vector Layer

A Vector Layer is a layer in digital art software like Krita that contains vector graphics. Vector graphics are resolution-independent and can be scaled without losing quality. In the video, the speaker mentions adding a vector layer and using it in conjunction with control layers and character poses, demonstrating the versatility of Krita's features in combination with the AI assistance plugin.


A simple plugin can add real-time AI assistance to Krita, allowing users to create artwork with AI guidance.

The process involves drawing basic shapes and then using the AI to generate the rest of the image.

Live stable diffusion technology enables users to create masterpieces in almost real time.

Crater and Comfy UI are key components in utilizing the AI for image generation.

If you have Comfy UI, you're halfway to using the plugin as it will install everything needed.

The plugin offers the benefits of an app like Creer, including various brushes and tools.

Stable diffusion can animate skeletons in real time, adding a new dimension to image generation.

System requirements for running stable diffusion are modest, needing only 6 GB of VRAM.

Linux or Microsoft Windows operating systems are recommended for the best experience.

The plugin can be downloaded from GitHub and installed into the Creer resources folder.

Enabling the plugin requires a few restarts of Creer and configuration through the settings.

For optimal performance, a new image size of 512 by 640 is recommended.

The plugin allows for easy connection setup to a local server managed by the plugin or an external server.

Comfy UI can be used to install required nodes and models for the plugin to function.

The plugin provides options to change models, prompts, and other settings for customization.

Live mode allows for real-time drawing assistance with a strength bar to control the level of AI influence.

Control Nets can be used in real time to manipulate and pose characters within the artwork.

Free-form scribbling without prompts lets the AI interpret and generate images from basic sketches.

Users can copy and modify generated images, such as changing eye color or other features.

The plugin offers a wide range of creative possibilities, including integrating existing images into new artwork.