Verified project record

Acly/krita-ai-diffusion

A Krita plugin that integrates diffusion-based generative AI into the image editing workflow, supporting inpainting, outpainting, live painting, and upscaling. It requires a local or remote ComfyUI backend and supports CPU execution, though a GPU with at least 6 GB VRAM is recommended for local generation.

Project overview

Project type: Image & Vision
Use cases: Image Processing
Deployment: Refer to project documentation
License: GPL-3.0

Best for

Creators and general users who edit existing images and require localized generative adjustments, such as expanding borders or filling specific selections.
Users who need to integrate structural guides, including line art or pose estimation, into the diffusion generation process.

Key capabilities

Uses existing image selections for generative fill, image expansion, and adding or removing objects.
Interprets the canvas in real time, providing immediate AI feedback during the drawing process.
Upscales and enriches images to resolutions reaching 4k, 8k, and beyond while managing memory constraints.
Directs the generation process using structural inputs such as Scribble, Line art, Canny edge, Pose, Depth, Normals, and Segmentation.
Supports the use of reference images, style and composition transfer, and face swap functionality.
Assigns individual text descriptions to distinct image areas defined by layers.
Allows users to queue and cancel generation jobs concurrently, preview results, and review previous prompts and outputs.
Enables the creation of presets utilizing custom checkpoints, LoRA, and samplers.

Limitations and risks

Local execution requires a graphics card with at least 6 GB VRAM. Without this hardware, processing is very slow or may fail.
The plugin cannot function independently and requires a configured ComfyUI backend.

Getting started

Install Krita, download the plugin ZIP file, and import the Python plugin from the file menu inside Krita.
Restart Krita, open an image, display the AI Image Generation docker, and click Configure to initiate the local server installation.

Evidence and sources

GitHub project description: Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.
GitHub repository metadata: generative-ai, krita-plugin, stable-diffusion
README: * **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 avai…
README: * **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. [Watc…
README: * **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 cont…

Reviewed at: 2026-07-18T02:56:54Z