AI-Powered Photo Editing Model DragGAN Has Been Released
The model's code is now available for free via GitHub.
A team of researchers behind DragGAN, an innovative AI-powered model for manipulating generated images first unveiled back in May, has released the model's code, making DragGAN officially available.
For those unaware, DragGAN enables one to "drag" any points of a generated image to precisely reach target points in a user-interactive manner, allowing the user to flexibly edit images while maintaining complete control over the pixel placement.
The method comprises two key components. The first component is feature-based motion supervision, which guides the movement of the handle point towards the desired position. The second component involves a novel point tracking approach that utilizes discriminative GAN features to continuously localize the handle points' positions.
You can learn more about DragGAN and access its code via GitHub. Also, don't forget to join our 80 Level Talent platform and our Telegram channel, follow us on Instagram and Twitter, where we share breakdowns, the latest news, awesome artworks, and more.
