A Crowd Shot is a wide or extremely wide framing that captures a large number of people in the same frame, emphasizing the scale, energy, or density of a group rather than focusing on individual faces or actions. It is commonly used to establish the size of gatherings, convey the atmosphere of public events, or show the relationship between individuals and the mass of humanity around them.

Crowd shots appear frequently in scenes depicting protests, concerts, sporting events, battle sequences, and urban environments where the sheer number of people is itself a visual subject. The framing is typically wide enough to show the full scope of the crowd, and the camera may be positioned at an elevated angle to maximize the sense of scale. In narrative filmmaking, crowd shots are also used to create contrast with close-ups, moving from the anonymity and chaos of the mass to the intimacy of a single character's experience within it.

In AI image and video generation, crowd shots are technically demanding because they require the model to generate large numbers of individual figures with plausible variation, spatial distribution, and realistic interaction. While modern AI models have improved significantly in handling crowd scenes, the quality and believability of generated crowds can still vary, making it useful to specify the density, activity, and spatial arrangement of the crowd in the prompt for better results.