# ant-research/MagicQuill

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

Repository: https://github.com/ant-research/MagicQuill
Canonical: https://ross.abutalabs.com/products/magicquill
Homepage: https://magicquill.art
Language: Python
License: NOASSERTION
License Family: other
Topics: aigc, image-editing, mllm, gradio
Last push: 2025-12-03T03:52:38+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 55, release rhythm 35, longevity 47
- inputs: {"age_days": 659, "days_push": 273, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3688, forks 389 (observed 2026-08-28T04:08:14.708806+00:00)

## What it is
MagicQuill is an intelligent interactive image editing system from a CVPR 2025 paper, combining a brush-based UI with AI-powered suggestions for precise local image edits. It ships as a Python/Gradio application with a ComfyUI custom node and pretrained checkpoints.

## Use cases
- edit images with brush strokes and AI suggestions
- add or remove objects in a photo precisely
- run a local gradio demo for interactive image editing
- use MagicQuill as a ComfyUI custom node
- reproduce CVPR 2025 image editing research

## When to choose
- you need precise, stroke-guided local image editing
- you want a ready-made gradio demo or ComfyUI integration
- you are reproducing or building on the MagicQuill paper

## When to avoid
- you need batch or automated image processing without interaction
- you lack a GPU or the required hardware
- you need a permissively licensed library for commercial embedding

## Facets
- artifact type: application
- maturity: active
- function: image-processing, machine-learning, ui-components
- domain: image-processing, artificial-intelligence, computer-vision
- platform: python, cross-platform
- tags: image-editing, diffusion, gradio, cvpr-2025, aigc, comfyui, interactive-editing, docker

## Member repositories
- ant-research/MagicQuill (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:14.708806+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:31:08.600967+00:00, confidence not recorded.
  - readme: https://github.com/ant-research/MagicQuill (fetched 2026-08-28T04:08:14.708806+00:00, sha 76da3aded3c3)
  - homepage: https://magicquill.art (fetched 2026-08-29T09:24:50.432490+00:00, sha 0f45f813761f)
- Data as of 2026-08-30T08:39:29.467469+00:00.