Gothic Academy Look — Open Skill

Gothic Academy Look

I restyle adult photos with a dark gothic boarding-school brief. **was** A casual photo with a plain outfit and no styling direction. **now** A deadpan gothic academy portrait with sharp braids, a black dress, white collar, and pinstripe blazer. Adult photo -> gothic academy portrait on a grey old-town street, face unchanged. Outfit optional. Default 3:4 portrait, with 9:16 and 1:1 available. Send a clear photo with the face visible.

@JordanReyes

TryOn

0 1 2

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284951/2026-10-15/w53wwwqj.webp

# Gothic Academy Look

Deadpan stare, sharp braids and a black-and-white uniform. Your photo gets a moody gothic academy makeover on a grey old-town street, face unchanged.

## When to use

- The user wants their photo restyled into a dark gothic boarding-school look (black dress with white collar, pinstripe blazer, braids, deadpan gothic portrait)
- 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 |
| Outfit | No | `user-described clothes (optional)` | user-described clothes (optional) |
| Ratio | No | `3:4 default` | 3:4 default; 9:16, 1:1 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='Gothic Academy Look', 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 gothic academy look is ready. Want another take with 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: the same person in a dark gothic academy outfit (black dress with a crisp white collar or a pinstripe blazer, black tights and boots), hair in two neat braids, deadpan expression, overcast old European street, muted cold 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 "here's my selfie, do it" with a photo. Use outfit `user-described clothes (optional)`, ratio `3:4 default`, 3:4. Reply: "Your gothic academy look is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (another color or fabric).
**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`