Double Exposure Movie Poster · Open Skill 公開スキル

Double Exposure Movie Poster

was: I had one plain photo. now: I made a cinematic one-sheet with a themed double-exposure background, while the subject stays crisp in front. Add your adult photo and a scene description. The default output is a 9:16 portrait. For a cleaner result, use one clear image with the face visible.

@JordanReyes

Poster

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284951/2026-10-15/74j3stzf.webp

# Double Exposure Movie Poster

Name a theme and your photo becomes a film one-sheet: you stay crisp in front while the background melts into a double-exposure of that world, with a moody cinematic grade.

## When to use

- The user wants a movie-style poster where their photo is combined with a themed double-exposure background (cinematic one-sheet, silhouette filled with a scene)
- A variation on a previous result: a different layout

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult with the face clearly visible. Ask for another photo if the face is tiny, blurred, heavily covered or in profile |
| Description | Yes | — | What the user wants; merged into the prompt |
| Orientation | No | `9:16` portrait | Other ratios on request |

- If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use.
- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Read `references/image-edit.md` for prompt structure.
2. **Identity read**: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')`.
3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Double Exposure Movie Poster', entity_type='skill_generation')`. Merge the user's details and options into the template.
4. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely.
5. Reply in one or two sentences, e.g. "Your double exposure movie poster is ready. Want another take with a different layout?" Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: a cinematic vertical movie poster: the person sharp in the foreground, while the background is a dreamy double exposure of <theme> scenery blending into silhouettes and light, moody color grade, film poster layout with an optional short title only if the user gives one. <user details and options>. Clear focal hierarchy; any text short, in quotes and spelled exactly; no real brands. Lighting and materials described concretely; composition suited to portrait 9:16. Photoreal unless the style says otherwise, fully clothed, no text unless requested.
```

Quality bar: Keep on-image text short and in quotes; no real brand names or logos; one clear focal hierarchy.

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.
- The face changes: regenerate once with the identity clause first; then say so honestly.

## Examples

**Default**: the user says "here's my selfie, do it" with a photo. Use the tuned defaults, 9:16. Reply: "Your double exposure movie poster is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (a different layout).
**Missing input**: no photo was sent. Ask: "Send one clear photo where your face is easy to see, and I'll start."

## References

- `references/image-edit.md`