Deep-learning artificial intelligence algorithms are cutting-edge technologies that can use in generative art and other valuable applications in life. StyleGAN2 is an advanced generative algorithm trained on a large dataset of images to produce stunning results beyond human thought or prediction. The generated images are synthetically produced based on the patterns learned from the input datasets. In this work, I train StyleGAN2 on the paintings from the Tretyakov Gallery to produce a generative artwork. The resulting image surprisingly mimics a “dragon's eye”, which is extremely rare.