An Establishing Shot is a wide or extremely wide framing that opens a scene by showing the location, time of day, and spatial context in which the following action will take place. It orients the audience geographically and atmospherically, answering the questions of where and when before the narrative moves into closer coverage.

Establishing shots are a foundational element of visual storytelling grammar, providing the context that allows tighter shots to make sense. A typical establishing shot might show the exterior of a building before cutting inside to characters in conversation, an aerial view of a city before moving to street-level action, or a wide landscape shot before focusing on characters within that environment. The shot can convey information about location, weather, time period, socioeconomic context, and mood without requiring dialogue or exposition. In television and film, establishing shots are often repeated when returning to a familiar location to remind the audience where the scene is taking place.

In AI video generation, creating effective establishing shots helps anchor generated sequences in clear spatial and temporal contexts. Prompting for wide, contextual views that show environment and atmosphere before generating tighter character or action shots follows the same narrative logic that traditional filmmaking uses, helping AI-generated content feel structured and intentional rather than spatially ambiguous.