π₯ Colab Demo
Note for Colab, remember to select a GPU via
Runtime/Change runtime type
(代η ζ§θ‘η¨εΊ/ζ΄ζΉθΏθ‘ζΆη±»ε
).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
π Updates
- Tweak performance.
- Integrate into InternGPT
- Automatically determining the number of iterations.
- Custom Image with GAN inversion.
- Download generated image and generation trajectory.
- Controling generation process with GUI.
- Automatically download stylegan2 checkpoint.
- Support movable region, mutliple handle points.
- Gradio and Colab Demo.
Results of our implementation.
demo.mp4
Ensure you have a GPU and PyTorch, Gradio installed. You could install all the requirements via,
pip install -r requirements.txt
Lanuch the Gradio demo
python gradio_app.py
If you have any issuse for downloading the checkpoint, you could manually download it from here and put it into the folder
checkpoints
.
Official DragGAN β StyleGAN2 β StyleGAN2-pytorch
@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}
}