Diagrams are ubiquitous in physics, especially in physics education and physics problem solving. Problem solvers may generate diagrams to orient to a scenario, to organize information, to directly extract an answer, or as a tool of communication. In this study, we interviewed 19 undergraduate and graduate physics majors, asking them to solve 18 multiple-choice physics problems-with no prompting regarding diagrams-and then six diagramming tasks of situations similar to six of the multiple-choice problems. By comparing spontaneously generated and prompted diagrams, we identify different diagramming elements and features used by physics majors acting towards different ends (i.e., in different epistemic frames). We found that different physical contexts impact how critical it is to draw an accurate diagram, and that the differences in diagramming between cohorts (e.g., between lower-division undergraduate and graduate students) seem to be smaller than the differences within a cohort. We also explore implications for teaching and research.