Acly/krita-ai-diffusion

Generative AI for Krita

✨Features | ⭳ Download | 🛠️Installation | 🎞️ Video | 🖼️Gallery | 📖User Guide | 💬Discussion | 🗣️Discord

This is a plugin to use generative AI in image painting and editing workflows from within Krita. Visit www.interstice.cloud for an introduction. Learn how to install and use it on docs.interstice.cloud.

The main goals of this project are:

• Precision and Control. Creating entire images from text can be unpredictable.

To get the result you envision, you can restrict generation to selections, refine existing content with a variable degree of strength, focus text on image regions, and guide generation with reference images, sketches, line art, depth maps, and more.

• Workflow Integration. Most image generation tools focus heavily on AI parameters.

This project aims to be an unobtrusive tool that integrates and synergizes with image editing workflows in Krita. Draw, paint, edit and generate seamlessly without worrying about resolution and technical details.

• Local, Open, Free. We are committed to open source models. Customize presets, bring your

own models, and run everything local on your hardware. Cloud generation is also available to get started quickly without heavy investment.

[](https://youtu.be/Ly6USRwTHe0 "Watch video demo")

Features

• Inpainting: Use selections for generative fill, expand, to add or remove objects
• Live Painting: Let AI interpret your canvas in real time for immediate feedback. Watch Video
• Upscaling: Upscale and enrich images to 4k, 8k and beyond without running out of memory.
• Diffusion Models: Flux 2, Z-Image, Stable Diffusion 1.5, XL, Illustrious
• Edit Models: Make modifications to images via text instructions
• ControlNet: Scribble, Line art, Canny edge, Pose, Depth, Normals, Segmentation, +more
• IP-Adapter: Reference images, Style and composition transfer, Face swap
• Regions: Assign individual text descriptions to image areas defined by layers.
• Job Queue: Queue and cancel generation jobs while working on your image.
• History: Preview results and browse previous generations and prompts at any time.
• Strong Defaults: Versatile default style presets allow for a streamlined UI.
• Customization: Create your own presets - custom checkpoints, LoRA, samplers and more.

Getting Started

See the Plugin Installation Guide for instructions.

A concise (more technical) version is below:

Operating System

Windows, Linux, MacOS

Hardware support

To run locally a powerful graphics card with at least 6 GB VRAM (NVIDIA) is recommended. Otherwise generating images will take very long or may fail due to insufficient memory!

NVIDIA GPU	supported via CUDA (Windows/Linux)
AMD GPU	supported via ROCm (Windows/Linux)
Intel GPU	supported via XPU (Windows/Linux)
Apple Silicon	MPS on macOS 14+
CPU	supported, but very slow

Installation

1. If you haven't yet, go and install Krita! _Required version: 5.2.0 or newer_ 1. Download the plugin. 2. Start Krita and install the plugin via Tools ▸ Scripts ▸ Import Python Plugin from File...

• Point it to the ZIP archive you downloaded in the previous step.
• Check Krita's official documentation for more options.

3. Restart Krita and create a new document or open an existing image. 4. To show the plugin docker: Settings ‣ Dockers ‣ AI Image Generation. 5. In the plugin docker, click "Configure" to start local server installation or connect.

[!NOTE]

If you encounter problems please check the FAQ / list of common issues for solutions.

> Reach out via discussions, our Discord, or report an issue here. Please note that official Krita channels are not the right place to seek help with

issues related to this extension!

_Optional:_ Custom ComfyUI Server

The plugin uses ComfyUI as backend. As an alternative to the automatic installation, you can install it manually or use an existing installation. If the server is already running locally before starting Krita, the plugin will automatically try to connect. Using a remote server is also possible this way.

Please check the list of required extensions and models to make sure your installation is compatible.

_Optional:_ Object selection tools (Segmentation)

If you're looking for a way to easily select objects or remove background in the image, there is a separate plugin which adds AI segmentation tools.

Contributing

Contributions are very welcome! Check the contributing guide to get started.

Gallery

_Live painting with regions (Click for video)_ [](https://youtu.be/PPxOE9YH57E "Watch video demo")

_Inpainting on a photo using a realistic model_

_Reworking and adding content to an AI generated image_

_Adding detail and iteratively refining small parts of the image_

_Modifying the pose vector layer to control character stances (Click for video)_ [](https://youtu.be/-QDPEcVmdLI "Watch video demo")

_Control layers: Scribble, Line art, Depth map, Pose_

Technology

• Image generation: Stable Diffusion, Flux
• Diffusion backend: ComfyUI
• Inpainting: ControlNet, IP-Adapter