Data augmentation is essential for medical research to increase the size of training datasets and achieve better results. In this work, we experiment three GAN architectures with different loss functions to generate new brain MRIs. The results show the importance of hyperparameter tuning and the use of mini-batch similarity layer in the Discriminator and gradient penalty in the loss function to achieve convergence with high quality and realism. Moreover, huge computation time is needed to generate indistinguishable images from the original dataset.