Soft Studio Portrait · compétence Open Skill

Soft Studio Portrait

was: A plain reference without direction for hair, makeup, or outfit. now: I turn an adult photo into a front-facing studio portrait with soft cinematic light and a dark gradient backdrop. Photo -> true-to-life skin detail in a 3:4 frame. Options: Identity is optional, but I need Description to generate.

@JordanReyes

Beauty

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284951/2026-10-15/63dwgpvq.webp

# Soft Studio Portrait

Quiet, centered and beautifully lit. A soft cinematic key light, a dark gradient backdrop and true-to-life skin detail for a timeless studio portrait.

## When to use

- The user wants a clean front-facing studio portrait with soft cinematic light and a dark gradient background (headshot, beauty portrait)
- A variation on a previous result: a different light or setting

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Person photo | No | — | Optional; if given, the face is preserved |
| Identity | No | — | photo of the person |
| Description | Yes | — | What the user wants; merged into the prompt |
| Orientation | No | `3:4` portrait | Other ratios 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. Fill the template below from the user's description. Use the tuned defaults for anything they leave out; ask one short question only if the subject itself is unclear.
3. If a person photo is given: `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.')` and add the identity clause.
4. With reference images: `generate_image(prompt=<PROMPT>, input_urls=[refs...], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Soft Studio Portrait', entity_type='skill_generation')`; without: the same call with `model='t2i.hd'` and no `input_urls`.
5. **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.
6. Reply in one or two sentences, e.g. "Your soft studio portrait is ready. Want another take with a different light or setting?" Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
<if photo: The same adult from the reference: <identity line>.> Intentional changes: a text-free front-facing studio portrait of <adult person description> in everyday clothing, soft cinematic key light, dark gradient background, finely detailed natural skin, centered calm pose. <user details and options>. Professional composition, deliberate lens and light, rich environmental detail. 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: Give the shot a full brief: subject, action, location, composition, lens and light. Never leave a thin one-line prompt.

## 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". Use the tuned defaults, 3:4. Reply: "Your soft studio portrait is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (a different light or setting).
**Thin request**: the user gives one word. Fill the brief from the tuned defaults and generate; do not interrogate.

## References

- `references/image-edit.md`