Halloween Persona Forge · skill Open Skill công khai

Halloween Persona Forge

Halloween Persona Forge là một Open Skill công khai trên Digen. Mở ra để xem workflow này tạo gì.

@CalebMonroe

Roleplay

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284955/2026-10-17/7cex76sv.webp

# Halloween Persona Forge

Four Halloween selves, one face. Your photo becomes a 2×2 grid: vampire, witch, demon and zombie looks with costume, makeup and matching backgrounds.

## When to use

- The user wants four Halloween looks from one photo — vampire, witch, demon and zombie — with costume makeup and background changes while keeping the face (Halloween persona four-pack, costume identity grid)
- A variation on a previous result: 1:1 on request

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult, face clear. Ask for another photo if the face is tiny, blurred or hidden |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Ratio | No | `3:4 default grid` | 3:4 default grid; 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='Halloween Persona Forge', 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 halloween persona forge is ready. Want another take with 1:1 on request?" 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 2x2 grid of four Halloween portraits of the same adult with facial identity preserved in every panel: top-left elegant vampire in a high-collared black cape under moonlight, top-right classic witch with a brimmed hat and candlelit cottage, bottom-left horned demon with ember underlight in a basalt hall, bottom-right pale zombie with torn layers in a foggy graveyard; matching makeup and costume per panel, photoreal, fully clothed, non-gore. <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 ratio `3:4 default grid`, 3:4. Reply: "Your halloween persona forge is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (1:1 on request).
**Missing input**: no photo was sent. Ask: "Send one clear photo where your face is ea