Shadow Self Sketch · Open Skill 公開スキル

Shadow Self Sketch

was: I wanted a clean beauty shot with a little more attitude. now: I use the tool to place one clear adult photo beside a bold black-and-white ink-sketch double. Photo -> split portrait with a manga-style alter ego. Options: Change the alter ego style. The output stays in 3:4 portrait format, so use a clear, face-forward source photo.

@JordanReyes

Anime

0 0 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284951/2026-10-15/8h9fruw7.webp

# Shadow Self Sketch

Meet your shadow self. Your photo sits beside a bold black-and-white ink-sketch double with a cooler, edgier attitude, like a manga character sheet.

## When to use

- The user wants a split portrait of their photo paired with an ink-sketch alter ego (shadow self, manga sketch double, black-and-white drawing twin)
- A variation on a previous result: a stronger style intensity

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 |
| 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='Shadow Self Sketch', 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 shadow self sketch is ready. Want another take with a stronger style intensity?" 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 split portrait: the person as a real photo on one side and their alter ego as a bold black-and-white manga ink sketch on the other, edgier outfit and expression, graffiti textures, monochrome with one accent color. <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.

## 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 the tuned defaults, 3:4. Reply: "Your shadow self sketch is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (a stronger style intensity).
**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`