A great deal of lung-related infections including COVID-19 can be diagnosed in the early stages by examining the x-ray images. With the advancement in deep learning techniques, we can back this up to a great extent. For the formulation of such models, the complexion of the dataset used for them plays a key role. An inadequate dataset with an imbalanced class of samples adversely affects the performance of such models. Through this research work, we introduce an improved version of Auxiliary Classifier GAN (ACGAN) which is computationally much more efficient than the prior model for the augmentation of the dataset. The dataset used in this research work is highly imbalanced due to the lack of availability of covid-19 infected samples. The proposed GAN architecture has done a great job in solving this issue. After the augmentation phase, the dataset including the spawned new samples is fed into the detection network to evaluate the performance of the model. The use of pre-existing ImageNet weights and Adam as an optimizer helped to train the model at a quicker rate and the overall accuracy achieved was 95.67 and validation accuracy of 92.57 with a loss value reduced to 0.675.