The prompt
A medium shot of a detective's hand in the foreground, holding a single, spent bullet casing. The camera then performs a slow rack focus, shifting from the casing to reveal the anxious face of a witness in the background, now in sharp focus What it is
This is a text-to-video prompt for Veo, described in Google Cloud's Vertex AI video generation prompt guide. It describes a medium shot with a detective's hand in the foreground holding a single spent bullet casing. The camera then performs a slow rack focus, shifting from the casing to reveal a witness's anxious face in the background, now in sharp focus.
Who it's for
- Filmmakers and storyboard artists who want a cinematic focus-pull shot
- Developers and creators learning how to write camera-movement prompts for Veo
- Content creators making crime or detective-themed video clips
Requirements
Requirements
- Access to Veo video generation (the source is the Vertex AI video generation prompt guide)
- The prompt text itself, adapted with your own subject, foreground object and background person
Examples
Original detective scene
PromptA medium shot of a detective's hand in the foreground, holding a single, spent bullet casing. The camera then performs a slow rack focus, shifting from the casing to reveal the anxious face of a witness in the background, now in sharp focusExpected output: A clip starting with a sharp casing in a hand and a blurred background, then focus shifts to reveal the witness's anxious face.
Antique key and a nervous heir
PromptA medium shot of a lawyer's hand in the foreground, holding a single, tarnished brass key. The camera then performs a slow rack focus, shifting from the key to reveal the worried face of an heir in the background, now in sharp focusExpected output: A clip where focus moves from a brass key in the foreground to the heir's worried face behind it.
Torn photograph and a guilty suspect
PromptA medium shot of an investigator's hand in the foreground, holding a single, torn photograph. The camera then performs a slow rack focus, shifting from the photograph to reveal the guilty face of a suspect in the background, now in sharp focusExpected output: A clip where the torn photograph starts sharp, then the focus pulls to the suspect's guilty expression in the background.
Pros & cons
Pros
- Pro:Clearly specifies shot type, camera movement and end state in one short prompt
- Pro:Foreground-to-background structure gives a defined narrative reveal
- Pro:Easy to adapt by swapping the object and person
Cons
- Con:Does not specify lighting, setting, style or duration, so those are left to the model
- Con:Source gives no guarantee about how precisely the rack focus will be rendered
- Con:Only one example scene is provided, so other uses require your own adaptation
Tips
- Keep the foreground object and background face distinct so the focus shift reads clearly
- Name the emotion of the revealed face, as the source does with 'anxious'
- State the final condition ('now in sharp focus') explicitly
Variations
- Replace the object and person to fit other genres, such as a key and a worried heir
- Reverse the order to shift focus from the face back to the object
- Change the emotion of the revealed face, for example guilty or relieved