Abstract: Various embodiments described herein provide a virtual production system that comprises a set of skin machine-learning models, a set of upper-body machine-learning models, a memory storing instructions, and one or more hardware processors to perform several operations based on stored instructions. Operations can comprise receiving a first image depicting a three-dimensional figure in a posing position and dressed in select apparel. Operations can comprise using the set of skin machine-learning models to generate a second image, where the set of skin machine-learning models up-sample the skin of the three-dimensional figure to generate photorealistic skin. Also, operations can comprise using the set of upper-body machine-learning models to generate a third two-dimensional image, where the set of upper-body machine-learning models up-sample an upper portion of the three-dimensional figure to generate a photorealistic upper portion.

Abstract: Systems and methods herein describe an image manipulation system for generating modified images using a generative adversarial network. The image manipulation system accesses a pre-trained generative adversarial network (GAN), fine-tunes the pre-trained GAN by training a portion of existing neural network layers of the pre-trained GAN and newly added layers of the pre-trained GAN on a secondary image domain, adjusts the weights of the fine-tuned GAN using the weights of the pre-trained GAN, and stores the fine-tuned GAN. An image transformation system uses the generated modified images to train a subsequent neural network, which can access a face from a client device and transform it to a domain of images used for GAN fine-tuning.