# XingangPan/DragGAN

Canonical: https://openpick.ing/r/draggan
As of: 2026-11-16 20:30 UTC


DragGAN is an open source tool in Image and video generation with 35,692 GitHub stars (−8 in the last 7 days), a custom license, as of 16 Nov 2026.

## Answer
DragGAN lets you click points on a GAN-generated image and drag them to change the picture, such as moving a pose or shape.

## Takeaways
- Drag points on a GAN image to reshape or move parts of it
- Works with GAN-generated images; real images need GAN inversion first
- Official code for the SIGGRAPH 2023 DragGAN paper

## Use cases
- Reshape a subject's pose or outline in a GAN image
- Try the interactive GUI or Gradio demo to edit GAN images
- Experiment with pretrained StyleGAN models such as StyleGAN-Human or LHQ

## Fit for
- Researchers and developers exploring interactive GAN image editing
- Users with a CUDA GPU who want to run the official DragGAN code

## Not for
- People wanting a one-click hosted tool with no setup
- Editing real photos directly without a GAN inversion step

## Setup difficulty
hard

## Quick answers
### How popular is DragGAN?
35,692 GitHub stars. −8 in the last 7 days. As of 16 Nov 2026.

## Stats
- Category: Image and video generation
- 35,692 stars, as of 2026-11-16 20:30 UTC
- -8 stars in 7 days
- License: Custom license (Check the license). Not legal advice. License: https://github.com/XingangPan/DragGAN
- GitHub: https://github.com/XingangPan/DragGAN

## Head to head
- [CompVis/stable-diffusion vs XingangPan/DragGAN](https://openpick.ing/compare/stable-diffusion-vs-draggan)
- [AUTOMATIC1111/stable-diffusion-webui vs XingangPan/DragGAN](https://openpick.ing/compare/stable-diffusion-webui-vs-draggan)

Cite as: DragGAN on OpenPick, https://openpick.ing/r/draggan, data as of 16 Nov 2026.

AI-generated content. Content updated 2026-11-14 09:48 UTC.

See Methodology: https://openpick.ing/methodology · Disclaimer: https://openpick.ing/disclaimer