Two Photo Hybrid Portrait · öffentlicher Open Skill

Two Photo Hybrid Portrait

Two Photo Hybrid Portrait ist ein öffentlicher Open Skill auf Digen. Öffne ihn, um zu sehen, was dieser Workflow erstellt.

@LoganPierce

Beauty

1 0 2

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284957/2026-10-20/yrfyxghh.webp

# Two Photo Hybrid Portrait

Two faces, one unmistakable person. Both photos fuse into a single believable adult portrait — shared bone structure, mixed eye, brow and lip shapes, and a coherent hairstyle — lit as one real studio shot.

## When to use

- The user wants two face photos fused into one believable hybrid portrait that mixes the features of both people (two-photo face blend, hybrid portrait, combined-face portrait)
- A variation on a previous result: favor the first photo

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 |
| Balance | No | `even blend of both faces` | even blend of both faces (default), favor the first photo, favor the second photo, or user-described emphasis |
| Backdrop | No | `deep blue studio gradient` | deep blue studio gradient (default), charcoal seamless paper, warm sand studio wall, or user-described setting |
| Outfit | No | `plain crew-neck top` | plain crew-neck top (default), dark blazer, soft knit roll-neck, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 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**: 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='Two Photo Hybrid 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. "Done! Here's your two photo hybrid portrait. I can also try favor the first photo if you like." 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: a single believable adult hybrid portrait that reads as one real person built equally from both photos: blended bone structure, a nose and jaw between the two, mixed eye and brow shapes, a mouth that borrows from each face, skin tone averaged, one coherent hairstyle and hairline, natural pores and fine detail, wearing <outfit: plain crew-neck top (default), dark blazer, soft knit roll-neck>, seated against <backdrop: deep blue studio gradient (default), charcoal seamless paper, warm sand studio wall>, soft key light with a cool rim, 85 mm portrait lens, shallow depth of field, one consistent light direction, adult, fully clothed, tasteful. <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.