# OpenGVLab/DragGAN

Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）

Repository: https://github.com/OpenGVLab/DragGAN
Canonical: https://ross.abutalabs.com/products/opengvlab-draggan
Language: Python
License Family: other
Topics: draggan, image-editing, image-generation, gradio-interface, interngpt
Last push: 2023-07-17T03:01:01+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 85
- inputs: {"age_days": 1201, "days_push": 1143, "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 4946, forks 473 (observed 2026-08-28T04:09:03.655924+00:00)

## What it is
An unofficial full-featured Python implementation of DragGAN, the interactive point-based image manipulation method built on StyleGAN generative models. It provides a Gradio web demo, PyPI package, and local deployment on Windows, macOS, and Linux with open-source code and models.

## Use cases
- drag points on a generated image to deform a face or animal pose
- edit GAN-generated images interactively in a browser demo
- run DragGAN locally with a GPU on Windows, macOS, or Linux
- invert a custom photo into a GAN latent and manipulate it
- try StyleGAN2-ada models for higher-quality image editing
- experiment with the Drag Your GAN paper's algorithm in Python

## When to choose
- you want a ready-to-run DragGAN demo with online Colab and Gradio UI
- you need cross-platform local deployment via pip install
- you want to explore interactive point-based GAN image manipulation

## When to avoid
- you need the official reference implementation (XingangPan/DragGAN)
- you require a maintained project with a license or active development
- you need reliable editing of arbitrary real photos (GAN inversion is limited)

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, gui
- domain: image-processing, machine-learning, graphics
- platform: python, windows
- tags: draggan, gan, stylegan2, image-editing, gradio, generative-models, unofficial-implementation, linux, macos, docker

## Member repositories
- OpenGVLab/DragGAN (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:03.655924+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 2026-08-29T18:17:53.338880+00:00, confidence not recorded.
  - readme: https://github.com/OpenGVLab/DragGAN (fetched 2026-08-28T04:09:03.655924+00:00, sha 0cf25e789d92)
- Data as of 2026-08-30T08:39:29.467469+00:00.