robbyant-research/magicquill

[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 1 hour ago
Added to GitGenius on September 18th, 2026
Created on November 12th, 2024
Open Issues & Pull Requests: 47 (+0)
GitHub issues: Enabled
Number of forks: 394
Total Stargazers: 3,691 (+0)
Total Subscribers: 45 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 4.7 hours
Mean response time: 7.5 days
90th percentile: 12.1 days
Tracked items: 119

Most active contributors

Sign in to see contributor activity.

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 85% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 45
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 565 days
Stale 30+ days: 44
Stale 90+ days: 44

Recent activity

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

Top labels

  • enhancement (2)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

MagicQuill is an intelligent interactive image editing system that combines AI-powered suggestions with precise local editing capabilities through a user-friendly interface.

The system addresses the challenge of making image editing both intuitive and accurate by integrating multimodal large language models with editing tools. Users interact with the system through natural language and visual feedback, while the underlying AI provides intelligent suggestions to guide the editing process. The approach enables precise local modifications without requiring manual mask creation or complex parameter tuning.

The tool suits designers and content creators who want AI assistance during image editing workflows. It works well for projects where users benefit from intelligent suggestions alongside manual control, rather than fully automated editing. The system is accessible through a web interface built with Gradio, making it available without specialized software installation.

The project maintains active development with completed releases of the research paper, demonstration website, code and model checkpoints, a Gradio-based demo interface, and a ComfyUI integration for users working within that ecosystem. The codebase is written in Python and includes Docker container support for simplified deployment across different environments.