Gender Swap Portrait · skill pubblica Open Skill

Gender Swap Portrait

Candy gloss, quick change, same soul. I like that the outfit and scene stay put while the presentation flips. I use an adult photo for solo or group portraits. Recognizable identity cues stay intact, with a gender-swapped read. **floor notes:** - use a clear photo of each adult, and make sure you have the right to use it - leave scope on auto from photo, or choose soft or sharp - keep the source ratio, or request 3:4 or 1:1 - add a description that gets merged into the prompt post what you make, then check the details before you go.

@SiennaBrooks

Beauty

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284952/2026-10-17/fr5xpr88.webp

# Gender Swap Portrait

Same soul, flipped presentation. Solo or group portraits get a gender-swapped read while outfits, scene and recognizable identity cues stay intact.

## When to use

- The user wants a gender-swapped version of a solo or group portrait while preserving identity outfits and scene (gender swap portrait, identity-preserving genderbend)
- A variation on a previous result: emphasize soft presentation

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | Adults only. Clear faces required for each person to swap |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Scope | No | `auto from photo` | auto from photo (default), emphasize soft presentation, emphasize sharp presentation |
| Ratio | No | `keep source` | keep source (default); 3:4, 1:1 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='Gender Swap Portrait', 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 gender swap portrait is on the canvas. Next I can do emphasize soft presentation." 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 gender-swapped reinterpretation of the uploaded solo or group portrait: presentation and secondary sex characteristics adjusted while preserving recognizable identity cues, outfits, poses and scene layout, photoreal, adults only, fully clothed, non-explicit. <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 "this one" with a photo. Use scope `auto from photo`, ratio `keep source`, 3:4. Reply: "All set. Your gender swap portrait is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (emphasize soft presentation).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/image-edit.md`