Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

Haofeng Liu    Chenshu Xu    Yifei Yang    Lihua Zeng    Shengfeng He

News and Update

• [Apr 5th] v1.0.0 Release.

Installation

It is recommended to run our code on a Nvidia GPU with a linux system. Currently, it requires around 14 GB GPU memory to run our method.

To install the required libraries, simply run the following command:

conda env create -f environment.yaml
conda activate dragnoise

Run DragNoise

To start with, in command line, run the following to start the gradio user interface:

python3 drag_ui.py

Basically, it consists of the following steps:

Dragging Input Real Images

1) train a LoRA

• Drop our input image into the left-most box.
• Input a prompt describing the image in the "prompt" field
• Click the "Train LoRA" button to train a LoRA given the input image

2) do "drag" editing

• Draw a mask in the left-most box to specify the editable areas. (optional)
• Click handle and target points in the middle box. Also, you may reset all points by clicking "Undo point".
• Click the "Run" button to run our algorithm. Edited results will be displayed in the right-most box.

More result

License

Code related to the Drag algorithm is under Apache 2.0 license.

BibTeX

If you find our repo helpful, please consider leaving a star or cite our paper :

@misc{liu2024drag,
      title={Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation}, 
      author={Haofeng Liu and Chenshu Xu and Yifei Yang and Lihua Zeng and Shengfeng He},
      year={2024},
      eprint={2404.01050},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Contact

For any questions on this project, please contact liuhaofeng2022@163.com

Acknowledgement

This work is inspired by the amazing DragGAN. We also benefit from the codebase of DragDiffusion.

Related Links

• Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
• DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
• DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models
• FreeDrag: Point Tracking is Not You Need for Interactive Point-based Image Editing

Common Issues and Solutions

1. For users struggling in loading models from huggingface due to internet constraint, please 1) follow this links and download the model into the directory "local_pretrained_models"; 2) Run "drag_ui.py" and select the directory to your pretrained model in "Algorithm Parameters -> Base Model Config -> Diffusion Model Path".