Head Body Merge · Open Skill 公開スキル

Head Body Merge

this little merge fits my candy gloss mood. quick change, but the face and hair still land right. I can take the face and hair from one adult photo, then place them on the body from another adult photo. one believable person. tips from me: - keep both faces clear so scale and tilt stay believable - use natural match by default, then check the neck join - try keep body photo's lighting exactly for a closer match - start with 3:4, or use 2:3 and 9:16 for the layout **floor notes:** this is a head-and-body composite, so check the result before posting. what did you make? drop your glossy pop looks here.

@SiennaBrooks

Custom

5 1 4

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284952/2026-10-17/j45ez3wk.webp

# Head Body Merge

Head photo plus body photo, one believable person. Face and hair land on the new body at the right scale and tilt, with a clean neck join and matched light.

## When to use

- The user wants the head from one photo merged onto the body from another photo with natural head size, position and tilt (head body merge, face-and-hair onto another body, two-photo composite)
- A variation on a previous result: keep body photo's lighting exactly

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo of person 1 | Yes | — | Clear face, adult |
| Photo of person 2 | Yes | — | Clear face, adult |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Blend | No | `natural match` | natural match (default), keep body photo's lighting exactly |
| Ratio | No | `3:4 default` | 3:4 default; 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**: run `recognize_image` on each photo with the identity prompt (one compact line each).
3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo 1, photo 2], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Head Body Merge', 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 head body merge is on the canvas. Next I can do keep body photo's lighting exactly." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
Person 1: <identity 1>. Person 2: <identity 2>. Each keeps their own face. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: photo 1 supplies the head, face and hair; photo 2 supplies the body, outfit, pose and background. A seamless photoreal composite places the head from photo 1 onto the body from photo 2, preserving head size, position and tilt relative to the neck, matching skin tone across face and neck, color grade, light direction and grain, with a clean invisible neck join; fully clothed body, no extra limbs or artifacts. <user details and options>. The result reads as one untouched photo: head scale and tilt fit the body, skin tone and light match across the neck, nothing from photo 1's background remains. 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: Treat it as an exact composite: photo 1 gives only the head and hair, photo 2 gives everything else; scale, tilt and skin tone must match so the join is invisible.

## 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 blend `natural match`, ratio `3:4 default`, 3:4. Reply: "All set. Your head body merge is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (keep body photo's lighting exactly).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get star