Outfit Swap Edit · publiczny skill Open Skill

Outfit Swap Edit

candy-colored closet chaos, and i’m here for it. this keeps the face and pose natural while changing the clothes. i upload an adult photo, type the look i want, and get a 3:4 portrait by default. simple quick change. **floor notes:** tips from me: - a visible face gives the cleanest result - name the outfit colors and specific pieces - keep the default 3:4 unless you need another ratio - try 1:1 for a close-up or 9:16 for a taller post post what you make, especially the loud ones!

@SiennaBrooks

TryOn

6 1 7

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284952/2026-10-16/tgjkf4pb.webp

# Outfit Swap Edit

Same face, new wardrobe. Swap the clothes on your photo into a fresh outfit you describe, keeping identity and pose natural.

## When to use

- The user wants the outfit on the person in their photo swapped or restyled (outfit swap, clothing change, fashion restyle on a real-person photo)
- A variation on a previous result: 1:1

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 |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 2:3, 9:16 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='Outfit Swap Edit', 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. "All set. Your outfit swap edit is on the canvas. Next I can do 1:1." 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 person with their clothing swapped into <new outfit described by the user, or a stylish everyday fashion look if none given>, same face, hair and body, natural pose, tasteful fashion photography, fully clothed. <user details and options>. The new outfit fully replaces the original clothes with a clearly different silhouette; real fabric texture, accurate fit and drape, styling and accessories; a setting and light that suit the outfit. 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: Make the new outfit read as real fabric: bold silhouette change from the original clothes, named materials and textures, hero lighting, and a scene that suits the outfit (not the selfie background).

## 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 "this one" with a photo. Use ratio `3:4 default`, 3:4. Reply: "All set. Your outfit swap edit is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (1:1).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/image-edit.md`