joliGEN provides generative AI tools for image and video tasks using GANs and diffusion models.
DragGAN
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold.
About DragGAN
DragGAN is a code repository for the SIGGRAPH 2023 method for interactive point-based manipulation of GAN-generated images. It provides a GUI and a Gradio demo, with conda and pip setup, Docker instructions, and scripts to download pretrained StyleGAN2 weights, with additional support for StyleGAN-Human and LHQ weights.
The GUI edits GAN-generated images; editing a real image requires prior GAN inversion, such as with PTI, before loading the latent code and weights. The Docker image needs about 25GB of disk space, and use is subject to CC-BY-NC and Nvidia Source Code License terms, including preserving the "AI Generated" watermark.
Key features
- Interactive point-based manipulation of GAN-generated images
- GUI started with gui.sh on Linux/macOS or gui.bat on Windows
- Gradio demo run with visualizer_drag_gradio.py
- Docker visualizer based on NGC PyTorch repository with GPU flag
- Load pretrained StyleGAN2, StyleGAN-Human, and LHQ weights
- Load inverted latent code and weights to edit real images
Best for: Researchers and developers with StyleGAN models who can set up Python, conda, and pretrained weights.
Good for
- Provides both desktop GUI and Gradio demo options
- Works with StyleGAN2, StyleGAN-Human, and LHQ pretrained weights
- Includes Docker setup and macOS Silicon and CPU installation path
Watch out for
- GUI edits GAN-generated images directly; real images require separate GAN inversion
- Docker image requires about 25GB of disk space
- Use requires CC-BY-NC and Nvidia license terms and preserving AI Generated watermark
DragGAN at a glance
- Category
- AI & Machine Learning › AI Image Generators
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Platforms
- macOS
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
DragGAN alternatives
Tools and sites you could use instead, ranked by how closely they match.
Stable Dreamfusion supports text to 3D and image to 3D generation, with mesh export using NeRF and diffusion.
Open source
24 alternatives
This repository provides the Sygil WebUI, a web interface for Stable Diffusion.
Open source
24 alternatives
The biniou project provides a self hosted web interface for more than 30 generative AI tools and models.
Open source
24 alternatives
A Python library to remove unwanted pseudo-text from images generated by your favorite generative AI models (Stable Diffusion, Midjourney, DALL·E).
Open source
24 alternatives
Deep-Live-Cam performs real-time face swaps and creates video deepfakes from a single image, according to its repository description.
Open source
24 alternativesPopular in AI Image Generators
Well-known listings from the same topic.
FigureLabsfigurelabs.aiImagePromptGuruimagepromptguru.netAI SVGaisvg.artCGDreamcgdream.aiFlux.1 AIflux1.aiPixraypixray.com
DragGAN FAQ
How do I start the DragGAN GUI?
Run sh scripts/gui.sh on Linux/macOS or .\scripts\gui.bat on Windows, or run python visualizer_drag_gradio.py for the Gradio demo.
Can I edit a real photo?
First perform GAN inversion using tools like PTI, then load the new latent code and model weights to the GUI.
How do I get pretrained weights?
Run python scripts/download_model.py for StyleGAN2 weights; place StyleGAN-Human and LHQ weights under ./checkpoints.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.