Krita AI Diffusion
Generate and inpaint inside the Krita painting app.
- Stars
- 10.7K
- Forks
- 640
- Open issues
- 121
- Last commit
- 2026-10-03
Live from the GitHub API · updated 2026-10-15
What is Krita AI Diffusion?
This Krita plugin brings diffusion models into a real painting workflow: select a region and generate, refine sketches, use live painting mode, and control output with pose, depth and line-art layers. It manages a local ComfyUI backend for you or connects to a remote one.
Key features
- Inpainting and outpainting from Krita selections
- Live painting mode that renders as you draw
- Control layers (scribble, pose, depth, line art)
- Upscaling and regional prompts
System requirements
- Platforms
- Windows · macOS · Linux
- GPU
- NVIDIA recommended (6 GB+ VRAM); can use a cloud/remote ComfyUI server
- Notes
- Requires Krita 5.2 or newer.
How to install Krita AI Diffusion
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Krita plugin
- 1Install Krita 5.2+ and download the plugin .zip from GitHub Releases.
- 2In Krita: Tools → Scripts → Import Python Plugin from File…, pick the .zip and restart Krita.
- 3Open the AI Image Generation docker and let it install a local server, or connect to an existing ComfyUI.
Strengths
- Best option for illustrators
- Precise control with layers
Limitations
- Requires learning Krita
- Local backend needs a decent GPU
Krita AI Diffusion alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| Krita AI Diffusion Generate and inpaint inside the Krita painting app. | 10.7K | GPL-3.0 | — | |
| InvokeAI Professional creative engine with a unified canvas for Stable Diffusion and FLUX. | 28.6K | Apache-2.0 | 4 GB for SD1.5, 8 GB for SDXL, 10 GB+ for FLUX | |
| ComfyUI Node-based interface for diffusion models — images, video and audio. | 137.6K | GPL-3.0 | 4 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models | |
| IOPaint Erase objects, watermarks and people with AI inpainting (formerly Lama Cleaner). | 23.3K | Apache-2.0 | — | |
| Stable Diffusion WebUI (AUTOMATIC1111) The classic browser UI for Stable Diffusion with a massive extension ecosystem. | 165.1K | AGPL-3.0 | 4 GB minimum (with --medvram/--lowvram), 8 GB+ recommended | |
| Stable Diffusion WebUI Forge A faster, leaner fork of the A1111 WebUI with FLUX support. | 13.1K | AGPL-3.0 | 6 GB+ (FLUX NF4/GGUF variants run on 6–8 GB) |
Related models
FAQ
Is Krita AI Diffusion free?
Yes — Krita AI Diffusion is open-source software released under the GPL-3.0 license. Check the license (and any model weight licenses) before commercial use.
Does Krita AI Diffusion run on Windows, Mac and Linux?
Krita AI Diffusion supports: Windows, macOS, Linux.
What hardware do I need for Krita AI Diffusion?
NVIDIA recommended (6 GB+ VRAM); can use a cloud/remote ComfyUI server
How do I install Krita AI Diffusion?
1. Install Krita 5.2+ and download the plugin .zip from GitHub Releases. 2. In Krita: Tools → Scripts → Import Python Plugin from File…, pick the .zip and restart Krita. 3. Open the AI Image Generation docker and let it install a local server, or connect to an existing ComfyUI.
What are the best Krita AI Diffusion alternatives?
Popular alternatives include InvokeAI, ComfyUI, IOPaint, Stable Diffusion WebUI (AUTOMATIC1111). See the comparison table on this page.
Can I use Krita AI Diffusion online without installing it?
If you just want results, AiLoft runs top image models such as GPT Image 2.5 and Nano Banana Pro in the browser — no GPU or setup required.
Skip the install — generate images in your browser
No GPU, drivers or Python needed. Use GPT Image 2.5 and Nano Banana Pro online and compare them side by side.