Modern networks are increasingly reliant on machine learning (ML) techniques for a wide range of management tasks, ranging from security to performance optimization. Datasets of labeled network traces are essential for these tasks. However, a central impediment when training network-focused ML models is the scarcity of labeled network datasets. Synthetic network traces can augment existing datasets, yet existing techniques typically produce only aggregated flow statistics or a few selected packet attributes. These approaches are ineffective when model training relies on having features that are only available from packet traces. This shortfall manifests in both insufficient statistical resemblance to real traces and suboptimal performance on ML tasks when employed for data augmentation. We propose to develop generative artificial intelligence (AI) models to generate high-resolution synthetic network traffic traces. Our goal is to develop network traffic traces that have high statistical similarity to real data and improve ML model performance over current state-of-the-art approaches (e.g., GAN-based approaches).