sanster/iopaint

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 16 seconds ago
Added to GitGenius on August 28th, 2026
Created on November 15th, 2021
Open Issues & Pull Requests: 76 (+0)
GitHub issues: Enabled
Number of forks: 2,524
Total Stargazers: 23,344 (+0)
Total Subscribers: 7 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 14.4 hours
Mean response time: 18.8 days
90th percentile: 33.5 days
Tracked items: 139

How this project is maintained

100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Three people close 69% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 52
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 665 days
Stale 30+ days: 52
Stale 90+ days: 52

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • stale (153)
  • bug (19)
  • help wanted (2)
  • enhancement (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

IOPaint is an image inpainting and outpainting tool powered by state-of-the-art AI models.

The tool addresses the problem of removing unwanted objects, defects, watermarks, and people from images, as well as replacing content or extending images beyond their original boundaries. It works by integrating multiple AI models including specialized erasure models like LaMa and diffusion-based models such as Stable Diffusion variants, PowerPaint, and BrushNet. Users can select the appropriate model for their task—erasure for object removal or diffusion models for content replacement and outpainting—and apply it through an interactive interface.

IOPaint is suitable for anyone needing image editing capabilities without relying on cloud services or proprietary software. The tool runs entirely self-hosted and supports CPU, GPU, and Apple Silicon hardware, making it accessible across different computing environments. It offers both a web-based interface and platform-specific installers, including a Windows one-click installer and native macOS and iOS applications. The project provides access to multiple model options from the Hugging Face ecosystem, allowing users to choose based on their specific editing needs and hardware constraints.

The project maintains a substantial base of real-world adopters, as evidenced by the fact that almost all open issues are raised by outside users rather than the core team. Maintainers typically respond to new issues and pull requests within a day. Work in the issue tracker is dominated by bug reports, indicating active engagement with stability and reliability concerns.