Duo Scene Merge — Open Skill

Duo Scene Merge

Duo Scene Merge is a public Open Skill on Digen. Open it to see what this workflow creates.

@LoganPierce

Custom

1 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284957/2026-10-17/nehgm6su.webp

# Duo Scene Merge

Two images in, one believable frame out. Both characters stand together in one scene with matching light, perspective, scale and style, each keeping their own look.

## When to use

- The user wants two separate characters or people from two images placed together in one natural photo with matching light, perspective and style (merge two people into one photo, character pairing, duo composite)
- A variation on a previous result: back to back

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo of person 1 | Yes | — | Clear face, adult |
| Photo of person 2 | Yes | — | Clear face, adult |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Interaction | No | `side by side and friendly` | side by side and friendly (default), back to back, walking together, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 4:3 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**: run `recognize_image` on each photo with the identity prompt (one compact line each).
3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo 1, photo 2], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Duo Scene Merge', 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. "Done! Here's your duo scene merge. I can also try back to back if you like." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
Person 1: <identity 1>. Person 2: <identity 2>. Each keeps their own face. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: both subjects placed together in one coherent scene <scene: a sunny city park bench, side by side and interacting naturally (default), or the user's described scene>, each keeping their own face, hairstyle, outfit and art style unified into one consistent rendering, matching light direction, color temperature, perspective, scale and shadows, natural body language between them, shot as one real photograph or one consistent illustration, fully clothed. <user details and options>. Apply the style to the entire frame with its signature traits (medium, texture, palette, linework); the person stays recognizable under the style. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested.
```

Quality bar: Name the style's visual traits (medium, brushwork or render, palette, line quality) and apply them to the whole frame; keep the face's likeness readable under the style.

## 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 "use this pic" with a photo. Use interaction `side by side and friendly`, ratio `3:4 default`, 3:4. Reply: "Done! Here's your duo scene merge."
**Variation**: "one more please". Keep the same inputs and change one option (back to back).
**Missing input**: no photo was sent. Ask: "I need one cl