krita-vision-tools  by Acly

AI-powered image masking and editing tools for Krita

Created 2 years ago
694 stars

Top 49.1% on SourcePulse

GitHubView on GitHub
Project Summary

This repository provides AI-powered selection and background removal tools for the Krita digital painting application. It targets artists and designers seeking to streamline object masking and image manipulation workflows, offering single-click or bounding-box selection and efficient background removal.

How It Works

The plugin leverages several machine learning models for its functionality. Object selection utilizes the Segment Anything Model (SAM) and MobileSAM, enabling precise masking via point clicks or bounding boxes. A "Precise" mode offers higher quality masks at the cost of processing time. Background removal employs a BiRefNet model for foreground object extraction, and an alternative "Smart Patch" feature uses MI-GAN for inpainting small areas.

Quick Start & Requirements

  • Install by downloading the latest release zip from the releases page and importing it via Krita's "Import Python Plugin from File..." option (Tools > Scripts).
  • Requires Krita version 5.2.11.
  • Supported platforms: Windows, Linux.
  • Alternative ML models (.gguf files) can be downloaded and placed in a specified folder for potentially higher precision.

Highlighted Details

  • Offers two primary selection methods: "Select Segment from Point" and "Select Segment from Box."
  • Includes a "Background Removal" filter for extracting foreground colors.
  • Supports alternative ML models for improved mask quality.

Maintenance & Community

  • The project is actively maintained by Acly.
  • No specific community links (Discord, Slack) or roadmap are provided in the README.

Licensing & Compatibility

  • The repository does not explicitly state a license.
  • Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

Using versions other than Krita 5.2.11 may lead to crashes. The "Precise" selection mode can take several seconds depending on hardware. The README does not specify licensing or community support channels.

Health Check
Last Commit

1 month ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
5
Star History
33 stars in the last 30 days

Explore Similar Projects

Starred by Max Howell Max Howell(Author of Homebrew), Shizhe Diao Shizhe Diao(Author of LMFlow; Research Scientist at NVIDIA), and
1 more.

big-sleep by lucidrains

0%
3k
CLI tool for text-to-image generation
Created 4 years ago
Updated 3 years ago
Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), Simon Willison Simon Willison(Coauthor of Django), and
10 more.

LAVIS by salesforce

0.2%
11k
Library for language-vision AI research
Created 3 years ago
Updated 10 months ago
Feedback? Help us improve.