Body Optimizer · Open Skill 공개 스킬

Body Optimizer

hot pink candy gloss energy, with the same face and outfit still in frame. i like that it balances the figure for a more flattering silhouette. upload one clear adult photo, and it outputs a portrait by default. **floor notes:** **tips from me:** - use one clear adult photo with the face visible - portrait 9:16 is the default ratio - ask for 1:1, 3:4, 2:3, or 16:9 when needed - check the close-up, then view the full figure post what you make, i want to see your quick change.

@SiennaBrooks

Beauty

25 2 24

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284952/2026-10-15/pbu9dwxh.webp

# Body Optimizer

Same face, refined figure. Your photo is gently body-optimized for a more balanced, flattering silhouette without changing identity or clothes.

## When to use

- The user wants their photo body-optimized or figure-enhanced (body reshape, slimmer silhouette, more balanced proportions) while keeping the same face and outfit
- A variation on a previous result: 1:1

Not for: dramatic or unrealistic reshaping, face or skin retouching, group photos, or 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 |
| Ratio | No | `9:16 default` | 9:16 default; 1:1, 3:4, 2:3, 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='9:16', name='Body Optimizer', 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 body optimizer 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 a gently optimized, more balanced and flattering body silhouette, same face, hair, skin tone and outfit, natural proportions, tasteful fashion-editorial lighting, fully clothed. <user details and options>. Keep the edit realistic: natural anatomy for the person's build, clothing folds that follow the new silhouette, and straight background lines (door frames, tiles, horizons) with no warping near the body. Lighting and materials described concretely; composition suited to portrait 9:16. Photoreal, fully clothed, no text unless requested.
```

Quality bar: A subtle, believable refinement: the silhouette reads more balanced at a glance while face, outfit, pose, lighting and background stay the same. Check straight lines next to the body for bending before replying.

## 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 `9:16 default`, 9:16. Reply: "All set. Your body optimizer 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."
**Thin request**: only a photo and a word or two (e.g. "make it pop"). Use the tuned defaults above and generate; do not ask follow-up questions.

## References

- `references/image-edit.md`