Leveraging the latest conditional Generative Adversarial Networks (GANs) with spatially adaptive denormalization (SPADE), we establish a novel ensemble-based workflow that effectively captures complex geological patterns. The code performs Bayesian history-matching of “hard” well data and “soft” flow data. SPADE-GAN History-Matching is developed by the data-assimilation and optimization group at NORCE Norwegian Research Centre AS.