A long shot, also called a wide shot (WS), frames a subject in full within a broad environmental context, showing the complete figure from head to toe while also capturing a substantial portion of the surrounding space. The terms are used interchangeably in practice, though long shot more specifically describes the camera-to-subject distance while wide shot emphasizes the breadth of the field of view - a distinction that rarely matters in production or prompting contexts.

Long shots serve multiple functions in visual storytelling. As establishing shots at the opening of a scene they orient the viewer geographically, showing where action is taking place and the physical relationship between subjects and their environment. They provide visual scale that close-ups and medium shots cannot, making subjects appear small relative to their surroundings when that smallness is narratively significant. They emphasize isolation, vulnerability, or freedom depending on how surrounding space is framed and lit, and they function as re-establishing shots mid-scene, returning the viewer to broader spatial context after a series of close-up coverage.

When prompting AI video generation for long shots or wide shots, describing both the subject and their surrounding environment with equal attention produces the best results, since both elements carry compositional weight in this framing. Specifying "full body visible in wide environmental context," adding detail about the location, scale, and atmosphere, and noting the intended spatial relationship between subject and surroundings helps generate footage with the proper scale and sense of place that defines an effective wide shot.