Climate impact assessment studies strongly depend on fine representations of meteorological fields. Downscaling addresses the trade-off between data requirements and storage capacity, yet the faithful replication of extreme-value statistics and spatiotemporal consistency presents a persistent issue. We present an efficient generative AI model for spatiotemporal downscaling. Using coarse-resolution monthly fields as inputs, the model reconstructs sequences of daily fields with the enhanced spatial resolution. The AI-generated daily fields accurately reproduce spatial coherence, temporal persistence, and extreme-value characteristics, showing strong agreement with ground-truth daily observations. We look forward to applying this framework more effectively to future studies on the impacts of extreme events.