Abstract Despite the extensive progress in face sketch synthesis, existing methods are mostly workable under constrained conditions, such as fifixed illumination, pose, background and ethnic origin that are hardly to control in real-world scenarios. The key issue lies in the diffificulty to use data under fifixed conditions to train a model against imaging variations. In this paper, we propose a novel generative adversarial network termed pGAN, which can generate face sketches effificiently using training data under fifixed conditions and handle the aforementioned uncontrolled conditions. In pGAN, we embed key photo priors into the process of synthesis and design a parametric sigmoid activation function for compensating illumination variations. Compared to the existing methods, we quantitatively demonstrate that the proposed method can work well on face photos in the wild