Scene Backdrop Swap · عوامی Open Skill

Scene Backdrop Swap

After the beat drop, I wanted to keep the dancer and change the city street. I like that the adult stays put while the scene around them changes. **tips from me:** - use an adult photo where the face is clearly visible, not tiny, blurred, covered or in profile - name the scene directly, like a neon alley, studio or city street - keep the default 3:4 ratio, or choose 9:16 for a phone clip - upload an adult photo you have the right to use Post what you make, especially the city lights version.

@AvaLindqvist

Custom

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284954/2026-10-16/23rjsbw6.webp

# Scene Backdrop Swap

New world, same you. Keep the subject, swap the backdrop to any scene you name — city street, studio, beach, neon alley — with clean edges and matching light.

## When to use

- The user wants the background of their photo replaced with a new scene they describe (background swap, scene replacement, city-street backdrop)
- A variation on a previous result: default stylish city street)

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 | No | tuned default below | What the user wants; merged into the prompt |
| Scene | No | `user-described (required for best results` | user-described (required for best results; default stylish city street) |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 2:3, 9:16, 16:9 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='3:4', name='Scene Backdrop Swap', 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 scene backdrop swap. I can also try default stylish city street) if you like." 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: the same adult subject from the reference photo with the background cleanly replaced by <user-described scene, or a stylish city street if none given>, matching lighting and contact shadows, crisp subject edges, photorealistic scene replacement, preserve face, hair, outfit and pose. <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 scene `user-described (required for best results`, ratio `3:4 default`, 3:4. Reply: "Done! Here's your scene backdrop swap."
**Variation**: "one more please". Keep the same inputs and change one option (default stylish city street)).
**Missing input**: no photo was sent. Ask: "I need one