draggan¶

Summary¶

Number of checkpoints: 3
Number of configs: 3
Number of papers: 1
- ALGORITHM: 1

DragGAN (SIGGRAPH’2023)¶

Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold

Task: DragGAN

Abstract¶

Synthesizing visual content that meets users’ needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. Existing approaches gain controllability of generative adversarial networks (GANs) via manually annotated training data or a prior 3D model, which often lack flexibility, precision, and generality. In this work, we study a powerful yet much less explored way of controlling GANs, that is, to “drag” any points of the image to precisely reach target points in a user-interactive manner, as shown in Fig.1. To achieve this, we propose DragGAN, which consists of two main components: 1) a feature-based motion supervision that drives the handle point to move towards the target position, and 2) a new point tracking approach that leverages the discriminative generator features to keep localizing the position of the handle points. Through DragGAN, anyone can deform an image with precise control over where pixels go, thus manipulating the pose, shape, expression,and layout of diverse categories such as animals, cars, humans, landscapes, etc. As these manipulations are performed on the learned generative image manifold of a GAN, they tend to produce realistic outputs even for challenging scenarios such as hallucinating occluded content and deforming shapes that consistently follow the object’s rigidity. Both qualitative and quantitative comparisons demonstrate the advantage of DragGAN over prior approaches in the tasks of image manipulation and point tracking. We also showcase the manipulation of real images through GAN inversion.

Results and Models¶

Gradio Demo of DragGAN StyleGAN2-elephants-512 by MMagic

Model	Dataset	Comment	Download
stylegan2_lion_512x512	Internet Lions	self-distilled StyleGAN	model
stylegan2_elphants_512x512	Internet Elephants	self-distilled StyleGAN	model
stylegan2_cats_512x512	Cat AFHQ	self-distilled StyleGAN	model
stylegan2_face_512x512	FFHQ	self-distilled StyleGAN	model
stylegan2_horse_256x256	LSUN-Horse	self-distilled StyleGAN	model
stylegan2_dogs_1024x1024	Internet Dogs	self-distilled StyleGAN	model
stylegan2_car_512x512	Car	transfer from official training	model
stylegan2_cat_256x256	Cat	transfer from official training	model

Demo¶

To run DragGAN demo, please follow these two steps:

First, put your checkpoint path in ./checkpoints, e.g. ./checkpoints/stylegan2_lions_512_pytorch_mmagic.pth. To be specific,

mkdir checkpoints
cd checkpoints
wget -O stylegan2_lions_512_pytorch_mmagic.pth https://download.openxlab.org.cn/models/qsun1/DragGAN-StyleGAN2-checkpoint/weight//StyleGAN2-Lions-internet

Then, try on the script:

python demo/gradio_draggan.py

Citation¶

@inproceedings{pan2023drag,
  title={Drag your gan: Interactive point-based manipulation on the generative image manifold},
  author={Pan, Xingang and Tewari, Ayush and Leimk{\"u}hler, Thomas and Liu, Lingjie and Meka, Abhimitra and Theobalt, Christian},
  booktitle={ACM SIGGRAPH 2023 Conference Proceedings},
  pages={1--11},
  year={2023}
}