Generative models for image synthesis achieved remarkable success in recent years and enjoy a lot of practical applications. While initially they mainly focused on 2D images, recent research explored generative frameworks with partial 3D control over the underlying object in terms of texture, structure decomposition, novel view synthesis or lighting manipulation. In this talk the speaker presents an overview of the field, discusses concepts of some of the most important architectures, EG3D, and discusses recent papers in 3D GAN architecture, editing, and domain transfer. The talk explores a list of recent papers in this area and highlights the speaker's latest effort at his research group of building a 3D GAN without a 2D up-sampler (EpiGRAF).