Ghost Portrait Message · مهارة Open Skill عامة

Ghost Portrait Message

Q: Ask for a late-night haunting? A: Why not. I turn one clear adult photo into a pale, translucent spirit portrait. Q: Get the details right? A: Send a description if you want. I add the spirit’s name and a three-line message from the other side. Q: What photo works best? A: Use one clear image. A visible face works best. I keep the final result in a 3:4 portrait frame.

@MayaCalloway

Story

0 0 0

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

# Ghost Portrait Message

Your portrait as a spirit: pale, translucent and drifting, with its name and a three-line message from the other side worked into the art.

## When to use

- The user wants their photo turned into an eerie ghost portrait with the spirit's name and a short message from beyond written in the artwork
- 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 |
| 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='Ghost Portrait Message', 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 ghost portrait message is on the canvas. Next I can do 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: an original ghostly portrait of the person as a pale translucent spirit with eerie glow, with the spirit's name '<name>' and a three-line message '<message>' lettered into the artwork. <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 "this one" with a photo. Use the tuned defaults, 3:4. Reply: "All set. Your ghost portrait message is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (a stronger style intensity).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/image-edit.md`