We present an empirical evaluation of fMRI data augmentation via synthesis. For synthesis we use generative models trained on real neuroimaging data to produce novel task-dependent functional brain images. Analyzed generative models include classic approaches such as the Gaussian mixture model (GMM), and modern implicit generative models such as the generative adversarial network (GAN) and the variational autoencoder (VAE). In particular, the proposed GAN and VAE models utilize 3-dimensional convolutions, which enables modeling of high-dimensional brain image tensors with structured spatial correlations. The synthesized datasets are then used to augment classifiers designed to predict cognitive and behavioural outcomes. Our results suggest that the proposed models are able to generate high-quality synthetic brain images which are diverse and task-dependent. Perhaps most importantly, the performance improvements of data augmentation via synthesis are shown to be complementary to the choice of the predictive model. Thus, our results suggest that data augmentation via synthesis is a promising approach to address the limited availability of fMRI data, and to improve the quality of predictive fMRI models.