Skip to content

Composition

Composition decides what the viewer can see and how objects relate in the frame. Choose shot size, viewpoint, subject placement and the space needed for the next action. Russian terms: композиция.

Show the entire table with the closed box near the left edge and the courier’s hands on the right. Leave clear space between the hands and the box before it is opened.

Prepare the Image node or first frame with the intended layout. In Prompt for the model, describe movement within that space. A close-up cannot simultaneously show a full body and a tiny distant reaction.

Check crops, object count, left/right placement and whether the audience can understand the action without reading your prompt. A character-sheet benchmark found that detailed face inserts did not guarantee the requested full-body composition.

This technique is documented as an authoring or workflow practice. It is available only through the stated inputs and operations; it is not a new model parameter. An unrendered example is untested. A dated successful case is an observation for its exact model, version, quality and mode, not a guarantee for another scene. Choose a model by the required operation first.

Related guides: overhead, rack focus.

See the model–technique applicability matrix for connected operations, dated outcomes and configurations that remain untested.

Reviewed 14 October 2026 against the current Studio authoring contract and the evidence described above. No new paid render was made for this example.