How to install and use DragGAN? Four methods for online and local operation

DragGAN is a popular open-source AI image project and research that allows for flexible and precise control of the pose, shape, expression, and direction of static objects in images through dragging. It can achieve operations such as opening the mouth of animals, changing the angle of cars, and elevating mountains in the landscape. Recently, DragGAN’s team has launched and opened up its official implementation project on GitHub. This article will introduce how to run, install, and use DragGAN, including various methods for online and local use.
Article directory:
Running and using DragGAN online
Run through OpenXLab Puyuan
Running through Hugging Face
Using Google Colab
Local installation and use of DragGAN
Running and using DragGAN online
If you only want to get started and see the effectiveness of DragGAN, running it online is a better choice. Here, we will introduce three methods to use DragGAN online: OpenXLab, Hugging Face, and Google Colab.
Run through OpenXLab Puyuan
OpenXLab Puyuan is an AI model community and hosting platform launched by Shanghai Artificial Intelligence Laboratory, similar to the Hugging Face introduced below. The DragGAN team has provided an official implementation of the DragGAN project in OpenXLab, allowing users to access the website and run DragGAN to test drag and drop effects.
Running address: https://openxlab.org.cn/apps/detail/XingangPan/DragGAN
Running through Hugging Face
Hugging Face is a well-known open-source AI model community that brings together various types of AI models, datasets, and runtime spaces. After the DragGAN project was launched as an open source, its official team immediately created a project space on Hugging Face, which interested users can access at any time to test the running effect.
Running address: https://huggingface.co/spaces/DragGan/DragGan
Using Google Colab
Google Colab is a cloud platform launched by Google that allows users to write, run, and share Python code using the Jupyter Notebook environment. Google Colab is a free service that provides users with virtual machines, including access to high-performance CPU, GPU, and TPU resources, as well as pre installed libraries such as TensorFlow, PyTorch, and more. If you are a technician, you can choose this method, open the run address below, then select GPU in the settings and run the installation code and demonstration code block.
Running address: https://colab.research.google.com/drive/1mey-IXPwQC_qSthI5hO-LTX7QL4ivtPh?usp=sharing
Local installation and use of DragGAN
If you want to install and deploy DragGAN locally on your own computer, simply follow the instructions on the DragGAN GitHub project. Please download and install Git, Python, and Conda before proceeding. The specific steps are as follows:
Step 1: Clone the official DragGAN project
Open the command prompt or terminal, use the git command, and clone the official project to the folder you want.
Step 2: Set up CUDA and install Python environment
After cloning, use the cd command to enter the folder
Then set the Conda environment: (Note: If you are running a Mac, please edit the environment.yml file and delete it, as the Mac does not use NVIDIA’s GPU. Additionally, the Mac needs to be set to run on a CPU and configured in the terminal.)
Activate Conda environment:
Install related dependencies:
Step 3: Download the pre trained model
Using commands to download
Step 4: Set up the DragGAN GUI interface and run it
Use the command to download the interface based on Graph. After downloading and installing, copy the local address from the Running on local URL in the terminal. You can now run it in your local browser.
The above is the method for running DragGAN compiled by the AI toolkit. If you have any problems during installation and use, you can leave a message in the comments section or seek help in DragGAN’s official GitHub project.