With the recent improvements in computation power and high scale datasets, many interesting studies have been presented based on discriminative models such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) for various classification problems. These models have achieved current state-of-the-art results in almost all applications of computer vision but not sufficient sampling out-of-data, understanding of data distribution. By pioneers of the deep learning community, generative adversarial training is defined as the most exciting topic of computer vision field nowadays. With the influence of these views and potential usages of generative models, many kinds of researches were conducted using generative models especially Generative Adversarial Network (GAN) and Autoencoder (AE) based models with an increasing trend. In this study, a comprehensive review of generative models with defining relations among them is presented for a better understanding of LANs and AEs by pointing the importance of generative models.