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）
This tool helps graphic designers, artists, and content creators interactively edit AI-generated images. You input an existing AI-generated image and, by clicking and dragging points on it, you can precisely control elements like object position, shape, or pose. It allows for intuitive manipulation, like moving a cat's head or changing a horse's leg position, directly on the visual output.
4,967 stars. No commits in the last 6 months.
Use this if you need fine-grained control to adjust specific features within an AI-generated image through direct, point-and-click manipulation.
Not ideal if you want to generate images from scratch with text prompts, perform general image editing on photographs, or require highly precise, pixel-level manipulation for non-AI images.
Stars
4,967
Forks
482
Language
Python
License
—
Category
Last pushed
Jul 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OpenGVLab/DragGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017