# open-mmlab/PowerPaint

[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model. 一个高质量多功能的图像修补模型，可以同时支持插入物体、移除物体、图像扩展、形状可控的物体生成，只需要一个模型

Repository: https://github.com/open-mmlab/PowerPaint
Canonical: https://ross.abutalabs.com/products/powerpaint
Homepage: https://powerpaint.github.io/
Language: Python
License: MIT
License Family: permissive
Topics: aigc, generation, image-editing, image-inpainting, stable-diffusion
Last push: 2026-08-15T03:53:32+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 71
- inputs: {"age_days": 1002, "days_push": 18, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1107, forks 87 (observed 2026-08-28T04:03:36.732126+00:00)

## What it is
PowerPaint is a versatile image inpainting model (ECCV 2024) built on diffusion models that handles text-guided object insertion, object removal, shape-guided inpainting, and outpainting with a single model using learnable task prompts. It is released as Python code with pretrained weights on Hugging Face.

## Use cases
- remove unwanted objects from photos
- insert objects into images with a text prompt
- extend an image beyond its borders (outpainting)
- fill in missing or masked regions of an image
- generate objects with controllable shapes in a masked area
- retouch and edit photos with AI inpainting

## When to choose
- you need one model covering multiple inpainting tasks
- you want state-of-the-art text-guided object insertion or removal
- you need shape-controlled object generation via prompt interpolation
- you want an MIT-licensed research-grade inpainting model

## When to avoid
- you need a simple GUI photo editor without ML setup
- you lack a GPU or cannot run diffusion models locally
- you need video inpainting rather than images

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, computer-vision
- platform: python, cross-platform
- tags: image-inpainting, stable-diffusion, diffusion-model, object-removal, outpainting, eccv-2024, aigc, image-editing, gpu

## Member repositories
- open-mmlab/PowerPaint (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:36.732126+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 2026-08-30T06:44:02.924037+00:00, confidence not recorded.
  - readme: https://github.com/open-mmlab/PowerPaint (fetched 2026-08-28T04:03:36.732126+00:00, sha 285cfb57dec4)
  - homepage: https://powerpaint.github.io/ (fetched 2026-08-29T12:47:49.732748+00:00, sha 2356dd694694)
- Data as of 2026-08-30T08:39:29.467469+00:00.