According to news from IT House on June 28, researchers from the Max Planck Institute of Computer Science, MIT CSAIL and Google have recently studied a new method of controlling GAN called DragGAN, just click and drag to quickly adjust the subject of the photo position, posture, expression, size and angle, etc. The project is currently open source on GitHub. The researchers say their method outperforms SOTA in GAN-based operations and opens new directions for image editing. In the coming months, they hope to extend point-based editing to 3D generative models.