Awesome-DragGAN 🐉

DragGAN has been one of the most popular generative image editing model these days. It provide a brand new way to edit the image by interatively selecting target and source points on the image, giving the greater flexibility to users than existing text-based editing. Though constrainted to generative image manifold currently, the idea of DragGAN should inspired and have inspired a varity of following works.

Awesome-DragGAN is a curated list of the papers, repositories, tutorials, and anythings related to the DragGAN.

• Starting Point
• Papers
• Repositories
• Tutorials
• Pretrained GAN Models

Contributions are welcome!

Starting Point

Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold Xingang Pan, Ayush Tewari, Thomas Leimkühler, Lingjie Liu, Abhimitra Meka, Christian Theobalt [Code] [Project Page] [Official Implementation]

Papers

The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing Shen Nie, Hanzhong Allan Guo, Cheng Lu, Yuhao Zhou, Chenyu Zheng, Chongxuan Li [Project Page] [Code] Nov 2 2023

FreeDrag: Point Tracking is Not You Need for Interactive Point-based Image Editing Pengyang Ling*, Lin Chen*, Pan Zhang, Huaian Chen, Yi Jin [Project Page] [Code] July 10 2023

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models Chong Mou, Xintao Wang, Jiechong Song, Ying Shan, Jian Zhang [Code] July 5 2023

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing Yujun Shi, Chuhui Xue, Jiachun Pan, Wenqing Zhang, Vincent Y. F. Tan, Song Bai [Project Page] [Code] June 26 2023

Repositories

• DragDiffusion: Unofficial Implementation for DragDiffusion.
• DragGAN: Unoffficial Implementation by OpenGVLab.
• DragGAN: Unoffficial Implementation by Skim AI Technologies, with a streamlit interface.
• Drag3D: DragGAN meets GET3D for interactive mesh generation and editing.
• DragGAN-Windows-GUI: Packaged DragGAN Installtion for Windows.

Tutorials

• How DragGAN Works: A Technical Deep Dive
• DragGAN: Early Access and Local Deployment Tutorial

Pretrained GAN Models

• Stylegan2: Car, Cat, Church, Human Face, Horse
• StyleGAN2-Ada: Cat, Dog, Wild, Human Face, Painting Face, Brecahad
• StyleGAN-Human: Human
• Self-Distilled-StyleGAN: Bicycle, Dog, Elephant, Giraffe, Horse, Lion, Parrot