LCM for Krita - OVERPOWERED!!!!

Olivio Sarikas
15 Mar 202411:36

TLDRThe video introduces a powerful combination of LCM and CR for digital painting, leveraging AI to generate unique artworks without the need for traditional painting skills. It showcases three innovative workflows, including an avatar generator, full-resolution photo manipulation, and a pet creator, emphasizing the use of AI for creative expression. The tutorial guides viewers through installing and using CR and AI image diffusion, demonstrating how to create and refine images using style words, layers, and brush settings. The video concludes with a live stream announcement, encouraging viewer interaction.


  • 🎨 The video introduces a method of digital painting enhanced by AI, specifically using LCM combined with CR.
  • 🤖 The presenter has created three workflows to demonstrate the use of AI in generating avatars, applying glitch effects on full-resolution images, and creating anime-style characters.
  • 👥 An avatar generator is showcased, producing consistent character expressions with varied faces using face detailer.
  • 🌟 Randomization is utilized to create endless automated prompts for character generation with the press of a button.
  • 🖼️ A full-size, high-resolution photo can be used with a glitch effect in a way not typically possible with stable diffusion.
  • 🐾 The 'cavi pet Creator' workflow allows users to input any kind of pet and generate a similar styled image, such as a tiger, unicorn, or cat.
  • 💡 CR (Creta) is highlighted as free, open-source software available for Windows, Linux, and Mac.
  • 🔧 The tutorial provides a step-by-step guide on installing and setting up CR and the AI image diffusion plugin.
  • 🖌️ The AI image generation feature within CR includes options for styles, prompts, negative prompts, and various checkpoints.
  • 🎨 The video demonstrates the painting process with AI assistance, showing how it can generate an image based on a description and user input.
  • 📌 The presenter invites viewers to join a live stream for further exploration and fun, encouraging engagement with the content.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is how to use a combination of digital painting and AI to create artwork without the need for traditional painting skills.

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

    -LCM stands for Layered Composition Model, which is a feature that works in conjunction with CR (Creta) to enhance the AI-generated images.

  • What are the three workflows showcased in the video?

    -The three workflows are: an avatar generator that produces consistent characters with varying facial expressions, a full-resolution photo input that renders a glitch effect, and a pet creator that generates pets in various styles based on an input image.

  • How can the avatar generator create different facial expressions while maintaining character consistency?

    -The avatar generator uses a trick with a face detailer to change the emotion of the face while keeping the character's overall consistency.

  • What is the role of randomization in the avatar generator workflow?

    -Randomization is used to create an endless amount of automated prompts, resulting in completely different characters with the same facial expressions each time the user clicks on the CU button.

  • What are the system requirements for Creta (CR)?

    -Creta is available for Windows, Linux, and Mac, and it is open-source software, which makes it free to use.

  • How can users install the AI image diffusion plugin for Creta?

    -Users can download the plugin, unpack it into their PyCre folder, and then enable it through the Python plugin manager in Creta's settings.

  • What are some of the different control net extensions and models that users can install for AI image generation?

    -Users can install various control net extensions for SD 1.5 and SDL, as well as models like Realistic Vision, Dream Shaper, and Chuga Not XL.

  • How does the AI image generation process work in Creta?

    -Users can select styles, set prompts, and use layers to influence the AI-generated image. The generation process takes into account all visible layers, not just the active one.

  • What is the purpose of the brush icon in the AI image generation section?

    -The brush icon allows users to select between generate, appscale, and life options, with life being associated with the LCM feature.

  • How can users adjust the influence of their drawings on the AI-generated image?

    -Users can adjust the strength slider, which controls the D noise level, to determine how much their drawings affect the final image.



🎨 Introduction to AI-Enhanced Digital Painting

The video begins by introducing the audience to the powerful combination of LCM and CR, which enables individuals to create stunning digital paintings without needing traditional painting skills. The creator showcases three innovative workflows that demonstrate the use of AI for generating avatars with varying facial expressions while maintaining character consistency, rendering high-resolution images with glitch effects, and producing anime-style creatures using image-to-image inputs. The video emphasizes the ease of transforming any pet image into a creative work of art through these workflows. The creator also provides a link to Patreon for viewers to access the workflows and encourages the audience to download CR, highlighting its open-source nature and cross-platform availability.


💻 Setting Up CR and AI Image Diffusion

This paragraph delves into the technical setup required for using CR and AI image diffusion. It guides the viewers through the process of downloading and installing CR for Windows, Linux, and Mac, stressing its open-source and free nature. The video then explains the installation of the AI image diffusion plugin, detailing the steps for Windows users, including the directory path and the need to restart CR after installation. It also mentions the compatibility of the software with various GPUs and the process of enabling the plugin through the Python plugin manager. The paragraph concludes with instructions on configuring the AI image generation settings, including the selection of control net extensions and the setup of styles and checkpoints for the image generation process.


🖌️ Utilizing AI Image Generation and Editing Tools

The final paragraph focuses on the practical application of AI image generation within CR. It explains how to use the AI image generation tool, including the selection of styles, setting prompts, and adjusting the D noise strength for balance between AI-generated and user-created elements. The video demonstrates the use of layers, brushes, and color selection tools to enhance and modify the AI-generated image, showcasing the ability to quickly transform a standard prompt into a unique creation. The creator also introduces the LCM brush feature, which allows for the generation of animations and the copying of results to new layers for further editing. The video concludes with a teaser for an upcoming live stream and an invitation for viewers to engage with the content by liking the video and joining the live session.




LCM stands for Layered Composition Magic, a technique used in digital art and AI-generated images to combine multiple layers with different styles or effects. In the context of the video, LCM is used alongside CR (Crea) to enhance the capabilities of AI in creating detailed and stylistic images, allowing for a more dynamic and personalized artwork.

💡CR (Crea)

CR, short for Crea, is an open-source digital painting software that is used for creating 2D images and art. It is mentioned in the video as a platform where AI image generation and LCM can be utilized, highlighting its compatibility with AI tools to enhance the creative process.


Artificial Intelligence, or AI, refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. In the video, AI is used to power the digital painting process, enabling the creation of images and art through intelligent algorithms that can generate, modify, and enhance visual content.

💡Avatar Generator

An avatar generator is a tool or software that creates personalized avatars for users, often with customizable features and styles. In the video, the avatar generator is used to demonstrate the power of AI in conjunction with LCM, as it can produce avatars with consistent character details but different facial expressions, highlighting the ability to maintain character consistency while offering variation.


Randomization is the process of generating a variety of outcomes from a set of possibilities without any predictable pattern. In the context of the video, randomization is used to create an endless amount of automated prompts for the AI, allowing for the generation of diverse and unique characters each time the user interacts with the system.

💡Glitch Effect

A glitch effect refers to a visual distortion or error that is intentionally applied to an image or video to create an artistic or stylistic outcome. In the video, the glitch effect is used in combination with a full-size, high-resolution photo and the image to add a layer of complexity and visual interest to the final artwork.

💡Image to Image

Image to image is a concept where an input image is used to generate or influence the output image, often through AI algorithms that can interpret and transform visual data. In the video, this concept is applied to create an anime-style image using an input image and the AI tool, demonstrating how AI can adapt and apply styles to create new visual content.

💡Styles and Prompts

Styles and prompts are terms used in AI-generated art to guide the output of the AI. Styles refer to the specific visual characteristics or aesthetic themes that the AI should follow, while prompts are the descriptive words or phrases that give the AI a general idea of what to create. In the video, the speaker discusses setting up styles and prompts within the software to direct the AI's image generation process.


DNoise, or Denoising, is a term used in AI image generation to refer to the process of reducing noise or random variation in the generated image to achieve a clearer, more refined result. In the video, the speaker discusses adjusting the DNoise slider to control the influence of the artist's own drawings on the final AI-generated image.


Animation, in the context of the video, refers to the process of creating moving images or sequences through a series of still images or frames. The video discusses using the LCM in combination with animation features to create dynamic visual content, showcasing the versatility of the AI tools in generating not just static images but also animated sequences.


Layering is a technique in digital art where multiple layers of images or elements are stacked on top of each other to create a composite image. In the video, layering is emphasized as a key feature of the AI image generation process, allowing artists to use multiple layers without affecting the final rendering.


Introduction to becoming a master painter with AI and digital painting combination.

Avatar generator workflow that maintains character consistency with varying expressions.

Using a face detailer for emotion change in avatars.

Randomization technique for generating unique characters with similar expressions.

Demonstration of a full-resolution photo glitch effect in stable diffusion.

Introduction of an image-to-image workflow for anime style pet creation without IPA.

Guidance on downloading and installing CR (presumably Krita) for Windows, Linux, and Mac.

Instructions on installing and enabling AI diffusion plugin in CR.

Explanation of setting up the python plugin manager in CR for AI image diffusion.

Introduction to AI image generation feature in CR and its configuration.

How to use LCM with CR for real-time AI-assisted painting.

The importance of adjusting the D noise strength for creative control.

Demonstration of using layers in CR for AI-generated image modifications.

Tutorial on basic painting tools and color selection in CR.

Live demonstration of creating an image with AI, showing ease of use for beginners.

Tips on further customizing generated images and in-painting with CR.

Announcement of an upcoming live stream for a deeper dive into the discussed workflows.