acly/krita-ai-diffusion

Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 53 minutes ago
Added to GitGenius on September 5th, 2026
Created on September 1st, 2023
Open Issues & Pull Requests: 100 (+0)
GitHub issues: Enabled
Number of forks: 622
Total Stargazers: 10,554 (+0)
Total Subscribers: 82 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

Krita AI Diffusion is a plugin that integrates generative AI image creation and editing capabilities directly into Krita.

The plugin addresses the challenge of using AI image generation within a professional painting workflow. Rather than treating AI as a separate tool requiring parameter tuning, it embeds generation into Krita's native editing environment. Users can inpaint within selections, outpaint to expand images, apply live painting for real-time feedback, and guide generation using reference images, sketches, depth maps, and other control inputs. The tool supports multiple diffusion models including Flux, Stable Diffusion variants, and specialized edit models, along with ControlNet and IP-Adapter features for fine-grained control over output.

Adoption suits digital artists and illustrators who want AI assistance without leaving their primary editing application. The plugin works best for users comfortable with local model execution on capable hardware, though cloud generation is available as an alternative for quick starts. The project emphasizes open-source models and customization, allowing users to bring their own checkpoints and LoRA weights. It distinguishes itself from standalone AI image generators by prioritizing seamless workflow integration over extensive parameter exposure, with features like job queuing, generation history, and region-based text descriptions that support iterative creative work.

Development shows consistent engagement with users through active discussion channels and documentation. The project maintains support across Windows, Linux, and macOS platforms. Regular feature additions demonstrate ongoing expansion of model support and control mechanisms. The codebase remains actively maintained with responsiveness to user feedback and community contributions.