In one embodiment, a method comprises inferentially selecting one or more design animation modules based upon analysis of information obtained from digital visual media items and digital audio media items; and automatically creating an audiovisual work using the selected design animation modules. Audiovisual works can be automatically created based upon inferred and implicit metadata including music genre, image captions, song structure, image focal points, as well as user-supplied data such as text tags, emphasis flags, groupings, and preferred video style.