Chinese landscape painting mainly describes the natural landscape of mountains and water. It is an important branch of Chinese paintings. Currently deep learning models achieve significant success in many domains, such as image classification, object recognition, image style transformation and automated image generation. In this research, a Chinese landscape painting automated generation model based on generative adversarial networks (GAN) is proposed. The model is trained with Chinese landscape painting images from Internet. The depth of the network and loss function are properly designed. The generator and discriminator are trained in an adversarial manner and finally a well-trained generator is obtained. Compared with true Chinese landscape paintings, the proposed model can generate images with Chinese landscape painting style.