Body Proportion Retouch · skill pública Open Skill

Body Proportion Retouch

Body Proportion Retouch é uma Open Skill pública no Digen. Abra para ver o que este fluxo cria.

@CalebMonroe

Beauty

0 0 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284955/2026-10-17/97mvf2y3.webp

# Body Proportion Retouch

Balanced, not plastic. A full-body retouch that slims the waist, lengthens the legs and keeps head and hands naturally proportioned — still clearly you.

## When to use

- The user wants a full-body photo retouched with more balanced proportions — slimmer waist, longer legs, natural head and hand scale (body proportion retouch, full-body reshape polish)
- A variation on a previous result: moderate

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | Need a clear full-body adult photo. Ask again if cropped at the waist or face is hidden |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Intensity | No | `subtle` | subtle (default), moderate |
| Ratio | No | `keep source` | keep source (default); 3:4, 2:3 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**: `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='Body Proportion Retouch', 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. "Your body proportion retouch is ready. Want another take with moderate?" 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 in the uploaded full-body photo with tasteful proportion retouch: slightly slimmer waist, longer balanced legs, naturally scaled head and hands, identity face and skin tone preserved, realistic anatomy, original outfit and background kept, photoreal, 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 "here's my selfie, do it" with a photo. Use intensity `subtle`, ratio `keep source`, 3:4. Reply: "Your body proportion retouch is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (moderate).
**Missing input**: no photo was sent. Ask: "Send one clear photo where your face is easy to see, and I'll start."

## References

- `references/image-edit.md`