# JiauZhang/DragGAN

Implementation of DragGAN: Interactive Point-based Manipulation on the Generative Image Manifold

Repository: https://github.com/JiauZhang/DragGAN
Canonical: https://ross.abutalabs.com/products/jiauzhang-draggan
Language: Python
License: MIT
License Family: permissive
Last push: 2023-07-11T03:49:46+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 85
- inputs: {"age_days": 1202, "days_push": 1149, "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 2128, forks 157 (observed 2026-08-28T04:06:16.989732+00:00)

## What it is
A Python implementation of DragGAN, a research method for interactively manipulating generated images by dragging points on the generative image manifold of a StyleGAN2 model. It includes a dearpygui-based GUI demo and relies on pre-trained StyleGAN2 checkpoints.

## Use cases
- drag points to edit GAN-generated images
- reproduce DragGAN research results
- experiment with StyleGAN2 latent manipulation
- run an interactive demo of point-based image editing
- study generative image manifold manipulation

## When to choose
- you want an open-source reference implementation of the DragGAN paper
- you need a lightweight GUI demo for point-based GAN image editing
- you are doing research on GAN-based image manipulation

## When to avoid
- you need to edit real photographs (loading real images is not yet supported)
- you need a production-ready image editor
- you want masked or region-constrained editing (not implemented)

## Facets
- artifact type: library
- maturity: experimental
- function: image-processing, machine-learning, deep-learning, gui
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, windows
- tags: draggan, stylegan2, gan, generative-models, image-manipulation, pytorch, point-based-editing, linux, macos

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:16.989732+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 2026-08-30T02:52:25.912034+00:00, confidence not recorded.
  - readme: https://github.com/JiauZhang/DragGAN (fetched 2026-08-28T04:06:16.989732+00:00, sha b8513ac5fe65)
- Data as of 2026-08-30T08:39:29.467469+00:00.