Noir Fashion Portrait · skill pública de Open Skill

Noir Fashion Portrait

Q: Ask: After-hours outfits get too polite in bad lighting. Send one clear adult photo. A: Get: I restyle it as a dark couture editorial with deep shadows, sharp tailoring, and one hard light. Q: Ask: Want a different scene? Put the details in the description. A: Get: I use your description, then return a 3:4 portrait. Q: Ask: What lands cleanest? A: Get: A face-visible photo works best. One image, one description, no off-screen nonsense.

@MayaCalloway

TryOn

1 0 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/hputzehz.webp

# Noir Fashion Portrait

Deep shadows, sharp tailoring and a single hard light: your photo as a dark couture editorial.

## When to use

- The user wants their photo restyled as a dark, cinematic fashion editorial (moody high-fashion portrait, dark couture shoot)
- A variation on a previous result: another color or fabric

Not for: 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 |
| Description | No | tuned default below | 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. **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='Noir Fashion 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. "All set. Your noir fashion portrait is on the canvas. Next I can do another color or fabric." 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: a cinematic dark fashion editorial: the person in sleek black couture, low-key dramatic lighting, deep shadows, moody color grade. <user details and options>. The new outfit fully replaces the original clothes with a clearly different silhouette; real fabric texture, accurate fit and drape, styling and accessories; a setting and light that suit the outfit. 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: Make the new outfit read as real fabric: bold silhouette change from the original clothes, named materials and textures, hero lighting, and a scene that suits the outfit (not the selfie background).

## 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 the tuned defaults, 3:4. Reply: "All set. Your noir fashion portrait is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (another color or fabric).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/image-edit.md`