Example input
Performer in a silver jacket inside a chrome elevator.

Music video planning · Free utility
Document only the visual traits needed to keep a subject recognizable across scenes. Separate stable identity from expressions, poses, and actions that may change.
Indexable example
This is a static example, not a pre-generated claim. Your actual result depends on the input you provide.
Example input
Performer in a silver jacket inside a chrome elevator.
Example output
Stable: short dark curls, star earring on left ear, silver cropped jacket, black shirt. Location: brushed chrome walls, red indicator left of doors. Expressions and pose may change.
How it works
Use one authorized image that shows the important stable traits.
Lock identity and wardrobe while allowing action and expression to develop.
Attach the approved consistency text to every scene prompt.
Useful when
Keep the artist visual coherent across angles.
Document wardrobe, props, and recognizable traits.
Keep room geometry and key objects consistent across cuts.
Questions
No. It creates clearer constraints, but model and reference support determine the result.
Usually not. Expressions belong in each scene unless one is essential to the concept.
Only if you have the rights and consent needed for the intended processing and use.
Keep working
Generate frame prompts that share one visual bible while preserving the action and framing required by each shot.
Analyze what is actually visible, then add controlled movement without inventing unnecessary characters, objects, or scene changes.
Map the meaning and emotional turns of your lyrics to visible scenes. Repeated choruses can develop one motif instead of receiving unrelated images each time.
Next step