LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
PluginRising

Krita AI Diffusion

Plugin : A set of capabilities installed into an AI application or a host · requires krita

Plugin that brings AI generation and inpainting locally into the free painting software Krita.

The smoothest local AI retouching for those who already draw.

Overall score
8.5 /10
Security: nothing to flag
Utility
8.0
Reliability
10.0
Security
No caveat on record
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Classic image editing software does not offer AI image generation natively integrated into a digital painting workflow. Krita AI Diffusion fills this gap by adding AI generation, inpainting and refinement directly inside Krita, without leaving the application.

The plugin uses ComfyUI as its diffusion backend and supports several model families: Stable Diffusion 1.5, XL, Flux, Illustrious and Z-Image. It allows working on precise selections, guiding generation with control layers (scribble, line art, depth, pose), using reference images via IP-Adapter, and painting live with real-time visual feedback.

This plugin is aimed at illustrators, concept artists and digital painters who already use Krita and want to integrate AI into their creative process without relying on an online service. Everything runs locally on the user's machine, with the option to connect a remote server if needed.

It is not suited for people new to image editing or those who do not want to set up a technical environment: installation requires a graphics card with at least 6 GB of VRAM for acceptable performance, and setting up the ComfyUI server involves several steps.

What it offers

  • ·Generative fill (inpainting): add, remove or replace elements within a precise selection of the image.
  • ·Live painting: the AI interprets your canvas in real time and provides immediate visual feedback as you draw.
  • ·Image upscaling: increase resolution to 4K, 8K and beyond without running out of memory.
  • ·ControlNet control layers: guide generation with a scribble, line art, depth map, pose or segmentation.
  • ·Image reference and style transfer via IP-Adapter: use an existing image to steer style or composition.
  • ·Text regions: assign distinct text descriptions to different areas of the image defined by layers.
  • ·Job queue and history: queue multiple generation jobs, cancel them, and browse previous results and prompts.
  • ·Preset customisation: create your own styles with custom models, LoRA and samplers.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
krita
Host
krita
Licence
GPL-3.0
FR interface
Yes

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active
Last release
22 August 2026

Links and repository checked on 25 October 2026 · added on 1 October 2023

How to install Krita AI Diffusion

1. Install Krita version 5.2.0 or newer from krita.org. 2. Download the latest plugin release (ZIP file) from the project's GitHub releases page. 3. In Krita, go to Tools > Scripts > Import Python Plugin from File, then select the downloaded ZIP. 4. Restart Krita, open or create a document, then show the panel via Settings > Dockers > AI Image Generation. 5. In the panel, click "Configure" to start the automatic local ComfyUI server installation or to connect to an existing server. 6. Precaution: download only from the official GitHub page (github.com/Acly/krita-ai-diffusion) to avoid tampered files.

In the same category

Whole category Photo & image →