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

DragGAN

💥 Colab Demo | InternGPT Free Online Demo

An out-of-box online demo is integrated in InternGPT - a super cool pointing-language-driven visual interactive system. Enjoy for free.🍭

Note for Colab, remember to select a GPU via Runtime/Change runtime type (代码执行程序/更改运行时类型).

Due to the limitation of GAN inversion, it is possible that your custom images are distorted. Besides, it is also possible the manipulations fail due to the limitation of our implementation.

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

🌟 Updates

This project is now a sub-project of InternGPT for interactive image editing. Future updates of more cool tools beyond DragGAN would be added in InternGPT.

• Tweak performance.
• Automatically determining the number of iterations.
• Integrate into InternGPT
• Custom Image with GAN inversion.
• Download generated image and generation trajectory.
• Controlling generation process with GUI.
• Automatically download stylegan2 checkpoint.
• Support movable region, multiple handle points.
• Gradio and Colab Demo.

Demo

Results of our implementation.

Usage

Ensure you have a GPU and PyTorch, Gradio installed. You could install all the requirements via,

pip install -r requirements.txt

Launch the Gradio demo

python gradio_app.py

If you have any issue for downloading the checkpoint, you could manually download it from here and put it into the folder checkpoints.

Acknowledgement

Official DragGAN   StyleGAN2   StyleGAN2-pytorch

Citation

@inproceedings{pan2023draggan,
    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},
    year={2023}
}