DragGAN
Interactive point-based image manipulation using GANs.
About
DragGAN from the Max Planck Institute enables interactive point-based image editing on the generative manifold of a GAN. Users place handle and target points and drag them to deform, move, resize, or rotate parts of an image, and the model regenerates realistic results that follow the edits. It builds on StyleGAN and runs on CUDA GPUs, with CPU and Apple Silicon fallbacks. Released under a custom research license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Image/Video Editing
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Custom
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Practical image super-resolution model trained on diverse degradations.
Robust face restoration using codebook lookup transformer.
One-click Stable Diffusion app for macOS with Apple Silicon optimization.
AI-powered image inpainting tool for removing objects and defects from photos.
Optimized fork of AUTOMATIC1111 with better memory management and speed.
Feature-rich web UI for Stable Diffusion with extensive extension ecosystem.