This course explores AI (especially machine learning) techniques for creating visual content in images and videos. The objectives of synthesis research range from modelling statistical distributions of visual data to creating realistic, picture-perfect graphics. Additionally, we delve into interactive tools for artistic expression. Throughout the course, we will cover key machine learning algorithms, including classical methods like nearest neighbour, PCA, and Markov Random Fields, as well as deep learning models such as ConvNets, GANs, VAEs, and Diffusion models. Students will gain practical skills to build applications and create new visual effects using their own photos and videos.