Give each visible subject a stable descriptive label, then track actions separately within each shot. “The couple move toward the table” is ambiguous when only one person walks. Use appearance and screen position as temporary anchors, and re-establish those anchors after a cut instead of assuming left and right remain fixed.
Use labels that the footage can support
“Person in the ivory jacket” and “person in the dark waistcoat” are more useful than invented names or inferred relationships. Do not infer occupation, ethnicity or private identity from appearance. If the video itself establishes names and you are authorized to use them, keep the naming consistent with that evidence.
Screen position is useful but not permanent. A person on the left in a wide shot can be on the right after a reverse angle. Combine an appearance anchor with position in the current shot. If both people wear similar clothing, use another visible detail or note that identification is uncertain.
Make a subject-action grid
| Moment | Ivory jacket | Dark waistcoat | Shared space |
|---|---|---|---|
| Start | Stands beside the table | Faces the doorway | Closed box on table |
| Middle | Looks toward partner | Takes one step inward | Box remains untouched |
| End | Offers an open hand | Stops and looks down | No object exchange yet |
The grid prevents a broad summary from inventing synchronized movement. It also makes it easier to spot a missing reaction. If the source cuts away during an exchange, record the visible before and after states rather than inventing an unseen hand action.
Turn the grid into a local prompt
The person in the ivory jacket remains beside the table and turns their eyes toward the approaching partner. The person in the dark waistcoat enters from the doorway, takes one step and stops. At the end, the ivory-jacketed person offers an empty hand. The closed box stays on the table throughout.
This is an illustrative reconstruction, not an observation of an uploaded user clip. With your own footage, check the prompt against the actual frames. Distinguish an eye movement from a head turn and a held pose from an action the analyzer merely expects to happen.
Review cuts before transferring the description
Runway's official prompting guide includes positional ways to describe multiple subjects. Its usefulness here is clarity of reference, not a guarantee of identity tracking by every model.
Can I label people A and B?
Yes in a planning note, but connect each label to visible evidence. An unexplained letter may mean nothing to a generator, especially if no matching reference labels are supported.
What if a person is hidden behind someone else?
Mark the action as unknown during the occlusion. Resume description when visible evidence returns. A continuous story does not justify filling every gap with a guessed movement.
Filled acceptance record: two-person action map
This is a constructed editorial exercise, not a reported generation or software test. Its purpose is to make the decision observable before spending on a more complicated version.
| Review item | Hypothetical evidence | Decision and next action |
|---|---|---|
| Main requirement | Only the ivory-jacketed person reaches for the box. | Hold this candidate: replace the collective verb with separate subject actions. |
| Source relationship | The current source and proposed change remain separately identified. | Release the written brief for review only; a clear plan is not an approved generated clip. |
| Handoff | The record names the rejected behavior and the relevant interval. | Keep the source, candidate and decision together so the next revision can be judged against the same requirement. |
Watch the complete interval before isolating frames. Write down where the problem first becomes visible and whether it persists to the end. A later attractive frame does not cancel an earlier failure. Change the relevant input or production decision before adding unrelated style instructions. If an external editor is used, record that finishing step separately from generation.
Current Imagild boundary
Use /en/film-script to organize a written plan and /en/film-prompt only for a currently supported reference-video recreation workflow. Check the actual selected input roles. The old video-prompt and editor routes do not establish a native analyzer, exact camera lock, existing-clip editor or frame-complete transcript. Manual source review remains valid even when no automated analysis is available. External application instructions above belong to the named vendor, not to Imagild.
Source checked for the transferable planning principle
- Runway Image to Video Prompting Guide: distinguishes image-established appearance from instructions for motion and temporal progression. The vendor's supported modes and results are not an Imagild feature contract.
November 13, 2026 editorial update. The worksheet and proposed procedures are illustrative. No new generation, physical measurement, success-rate study, citation measurement or production deployment was performed.