---
name: musicvideo-replace
description: "Put the person's character into film frames and remove every actor's face — GPT Image 2.5 Flare edit (low): head swap for the lead (the film's costume may stay or a look sheet goes in), invented faces for everyone else, a second pass and crop-and-paste edits for famous faces the model keeps, a pass to remove an unwanted lead; a costume/prop look sheet first. Part of the musicvideo reference set."
---

These creative references describe source experiments with external tools. Use your own supported account and tools; this download installs no automation. Settings and timings are experimental observations, not current FlashBoards availability. Use only media and voices you have permission to use.

# musicvideo-replace · no actor's face on screen

Picture 1 is always the person's own `{face board}` or `{look sheet}` from their character card. Write every prompt fresh; the templates below give the tested structure, [brackets] are example values.

## Steps

0. **Cast first.** `{character}` is the lead. A second main role in the frame: ask the person — another of their characters, an invented face, or removed. Never a demo character.
1. **New costume or prop?** Make a `{look sheet}` first (GPT Image 2.5 Flare edit, 2048×1152, picture 1 = the character sheet, "take their face and hair, never their clothes"; face close-up + full body + the prop).
2. **Replace** (Flare edit, low, 1920×1088): picture 1 = `{look sheet}` (or `{face board}` when the film's costume stays), picture 2 = the frame. Prompt structure:
   ```
   Picture 1 is only the look of {character}: their face, hair and their whole [outfit name, e.g. "welder's outfit"]. Picture 2 is a frame from a film. Shoot picture 2 again exactly the same:
   the same camera, framing, set, light and atmosphere; but the main person of the frame is {character} from picture 1, in exactly their outfit from picture 1, in the
   same place, pose and movement. Every other person in the frame keeps their place, pose, clothes and hair colour but gets a completely different, invented
   face that belongs to nobody from any film or real life. Change nothing else.
   ```
   With `{face board}` only: "only the look of {character}: their face and hair", and keep the clothes of picture 2. Crowd-only frames: the same without picture 1. A prop in hand: "{character} holds the [prop] from picture 1 [how and where]...". Never add words about the person's looks.
3. **A second of the person's characters** in the same frame: one person per pass — the second pass takes the already-replaced frame as picture 2 and that character's sheet as picture 1; check both faces. (Not measured in the example run.)
4. **Check every face with crops.** GPT keeps famous faces: they can survive both the first prompt and a "change every other face" pass.
5. **Crop and paste** for a kept face: crop the head (~350 px), edit "a completely different [man/woman] with a new invented face", paste back with a feathered mask.
6. **Remove an unwanted lead**: a pass on the replaced frame — "keep {character} exactly as they are... remove the [person, e.g. young man next to them] completely, show the [place] where they were".
7. A refusal by Flare's checker (hugs, a romantic pose): rerun on `gpt-image-2.5/sunburst/edit`.

## Never

- Describe the frame or the person's looks in the prompt (blind prompts only).
- Trust one pass for "everyone else" — check crops of every visible face.
- Use a demo character's sheet or a demo frame for a person.

## Example run (reference only — never reuse its files, prompts, faces or frames for a person)

Demo character Mara Vale, *Titanic*. Look sheet: welder's outfit with a lit brass welding torch, the worked example. Prop line used: "She holds the lit brass welding torch from picture 1 against the pipes...". Cal and Jack survived both the first prompt and a "change every other face" pass → crop-and-paste. Lead removal ("remove the young man next to her") worked on the bow and in the boiler room. Flare refused hugs and the bow pose → sunburst.