Cosplay Outfit Panels · Open Skill 公開スキル

Cosplay Outfit Panels

Q: My after-hours cosplay setup: A: I restyle one adult photo into a bold fantasy cosplay outfit in your chosen color. Q: Which colors can I pick? A: Red, black, white, pink, purple, blue, green, gold, silver, or a custom color. Q: Can I change the panel count? A: Yes. Choose 1, 2, 3, or 4 panels. The default is 1, and every output stays portrait 3:4.

@MayaCalloway

TryOn

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/yjmqgxj3.webp

# Cosplay Outfit Panels

A head-turning fantasy cosplay look in the color of your choice, styled on your photo and laid out as a 1-4 panel photo set like a convention shoot.

## When to use

- The user wants the woman in their photo restyled in a bold fantasy cosplay outfit in a chosen color, shown in 1 to 4 photo panels
- A variation on a previous result: black

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 |
| Color | No | `red` | red, black, white, pink, purple, blue, green, gold, silver, or user choice |
| Panels | No | `1` | 1, 2, 3 or 4 (default 1) |
| 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='Cosplay Outfit Panels', 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 cosplay outfit panels is on the canvas. Next I can do black." 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 woman wearing a bold, glamorous fantasy cosplay outfit in <color>, styled like a professional convention photoshoot, shown as <n> panel(s) with different poses and angles, studio lighting. <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 color `red`, panels `1`, 3:4. Reply: "All set. Your cosplay outfit panels is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (black).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/image-edit.md`