Inpaint
Use Krita's selection tools to mark an area and remove or replace existing content in the image. Simple text prompts can be used to steer generation.
Generate images effortlessly within Krita
5K+Designer Like It
Krita AI Diffusion
Krita AI Diffusion is an innovative plugin that seamlessly integrates the power of Stable Diffusion, a cutting-edge AI model for image generation, into the open-source digital painting software Krita, enabling artists to leverage text prompts and selection tools to inpaint, outpaint, refine, and generate new artwork directly within their familiar Krita workspace, offering both local and cloud-based processing options for efficient and flexible AI-assisted creative workflows.
01 / Krita AI Diffusion Features
Use Krita's selection tools to mark an area and remove or replace existing content in the image. Simple text prompts can be used to steer generation.
Extend your canvas, select a blank area and automatically fill it with content that seamlessly blends into the existing image.
Create new images from scratch by decribing them with words or existing images. Supports SD1.5 and SDXL.
Use the strength slider to refine existing image content instead of replacing it entirely. This also works great for adding new things to an image by painting a (crude) approximation and refining at high strength!
Let AI interpret your canvas in real time for immediate feedback.Watch Video}
Guide image creation directly with sketches or line art. Use depth or normal maps from existing images or 3D scenes. Transfer character pose from snapshots. Control composition with segmentation maps.
Work efficiently at any resolution. The plugin will automatically use resolutions appropriate for the AI model, and scale them to fit your image region.
Upscale and enrich images to 4k, 8k and beyond without running out of memory.
Depending on hardware, image generation can take some time. The plugin allows you to queue and cancel jobs while working on your image.
Not every image will turn out a masterpiece. Preview results and browse previous generations and prompts at any time.
Versatile default style presets allow for a simple UI which covers many scenarios.
Create your own presets - select a Stable Diffusion checkpoint, add LoRA, tweak samplers and more.
02 / Krita Plugin Installation Guide
Follow the steps below to install the Krita AI Diffusion plugin and start generating images effortlessly within Krita.
If you haven't yet, go and install Krita! Required version: 5.2.0 or newer
Download the plugin from GitHub.
Start Krita and install the plugin via Tools ▸ Scripts ▸ Import Python Plugin from File...
Restart Krita and create a new document or open an existing image.
To show the plugin docker: Settings ‣ Dockers ‣ AI Image Generation.
In the plugin docker, click 'Configure' to start local server installation or connect.
03 / Wall of Love
If you enjoy using Krita AI Diffusion, please share your experience on Twitter with the hashtag
04 / Frequently Asked Questions
Have a question? Check out some of the common queries below.
Download the plugin from the official GitHub release page, then in Krita navigate to Tools ▸ Scripts ▸ Import Python Plugin from File... and select the downloaded ZIP file. After installation, restart Krita and enable the plugin docker through Settings ‣ Dockers ‣ AI Image Generation.
The plugin supports Windows, Linux, and MacOS. Additional requirements like Python and venv must be installed on Linux and MacOS, typically available through the system's package manager.
A powerful graphics card with at least 6 GB of VRAM is recommended. The plugin supports NVIDIA GPUs via CUDA, AMD GPUs via DirectML on Windows and ROCm on Linux, Apple M1/M2 via MPS on macOS, and CPUs, although CPU usage is significantly slower.
Yes, the plugin allows you to create new images from scratch using text prompts or existing images. Features such as inpaint, outpaint, and refine help control and direct the generative process.
You can use an existing installation of the ComfyUI backend or install it manually. If the server is running locally or remotely before you start Krita, the plugin will automatically try to connect.
Yes, the plugin allows you to guide image creation using sketches or line art. You can also utilize depth or normal maps from existing images or 3D scenes to influence the composition.
The plugin supports upscaling to 4k, 8k, and beyond, enabling enhancement of image quality and detail without overwhelming system resources.
Contributions are welcome, and you can begin by reviewing the contributing guide on the project's GitHub page. This may involve improving existing features, adding new functionalities, or addressing bugs.
The 'Inpaint' feature allows you to select an area in your image to either remove or replace content, using simple text prompts to guide the AI in generating new content that matches the surrounding image.
The 'Outpaint' feature enables you to extend your canvas and fill the new areas with content that blends seamlessly with the existing artwork. This is useful for expanding scenes or adding new elements to your compositions.
The 'Refine' feature lets you adjust the strength of the AI's effect on existing content, allowing for subtle modifications or more extensive enhancements without completely replacing elements.
Yes, a separate plugin called 'AI segmentation tools' can be used in conjunction with the Generative AI plugin to facilitate easier selection and manipulation of objects within the image.