In this article, we present a strategy for packing realistic crystals, critical for mesoscale simulations, and predictions. The current packing code uses a dynamic algorithm, with crystal shapes represented by level sets, to create appropriate packs of the microstructure for an energetic material. Crystal shapes include the nitramines HMX, RDX, PETN, and CL20. Two series of packs are considered: a bidisperse pack with size ratio 1:0.3 and a polydisperse pack. We also construct equivalent packs of spheres for comparison purposes. Higher-order statistics are computed and compared. We show that the second-order statistics are essentially independent of particle shape when the packing fraction is held constant. The second-order statistics do, however, depend on the polydispersity.