#1212th of 56 in Image and videoFor image, video and design, image and design
krita-ai-diffusion
Krita plugin for inpainting, live painting and upscaling with diffusion models
- Stars
- 10.9k
- License
- GPL-3.0
- Last commit
- Oct 2026
- Last release
- Aug 2026
- Language
- Python
9,890 on 21 Apr 202610,873 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Krita plugin that adds generative image tools to the painting canvas: selection-based inpainting and expand, live painting, upscaling, and text-instruction edit models. It uses ComfyUI as the backend, either installed automatically from the plugin, pointed at an existing local or remote server, or via cloud generation. Supports Flux 2, Z-Image, Stable Diffusion 1.5, SDXL and Illustrious, with ControlNet, IP-Adapter and per-region prompts.
Who it is for: Digital artists who want local diffusion tools inside Krita
Strengths
- Works on Krita selections and layers, with per-region prompts defined by layers
- ControlNet and IP-Adapter support: scribble, line art, depth, pose, style and face reference
- Can install a local ComfyUI server or connect to an existing or remote one
- Custom presets for checkpoints, LoRA and samplers; runs on NVIDIA, AMD, Intel and Apple Silicon
Weaknesses
- Requires Krita 5.2.0 or newer; unusable outside Krita
- CPU generation is supported but described as very slow
- Object selection and segmentation need a separate plugin (krita-ai-tools)
- Custom ComfyUI setups need specific extensions and models installed manually
What it needs
- GPU optional
- Needs Krita 5.2.0+, ComfyUI
- Models: Flux 2, Z-Image, Stable Diffusion 1.5, SDXL, Illustrious
Quick answers
Is krita-ai-diffusion open source?
Yes. Its code is on GitHub under the GPL-3.0 license.
Does krita-ai-diffusion need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Image and video
See all 56| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 92 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 86 out of 100 |
| #4 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |
| #5 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 85 out of 100 |