Spirit Photography Portrait · skill pública de Open Skill

Spirit Photography Portrait

Spirit Photography Portrait es una Open Skill pública en Digen. Ábrela para ver qué crea este flujo.

@HarperDiaz

Story

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284956/2026-10-19/vmd4mtuu.webp

# Spirit Photography Portrait

A veiled figure half dissolves into the staircase light. Late-19th-century plate photography with an unnerving double-exposure glow — antique, hushed and slightly wrong.

## When to use

- The user wants an antique late-19th-century spirit photograph with a ghostly veiled figure and an eerie atmosphere (spirit photo generator, vintage seance portrait, ghostly Victorian photograph)

Not for: Editing an existing photo (use an image-edit skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Apparition | No | `veiled woman` | veiled woman (default), man in a dark frock coat, child-sized silhouette, or user-described |
| Setting | No | `wooden staircase` | wooden staircase (default), parlor with floral wallpaper, conservatory with ferns, or user-described |
| Decay | No | `subtle` | subtle (default), heavy plate damage, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 2:3, 1:1, 9:16 on request |

- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Expand the user's idea into the brief below. If they gave almost nothing, use the tuned defaults instead of asking.
2. `generate_image(prompt=<PROMPT>, model='t2i.hd', orientation='portrait', aspect_ratio='3:4', name='Spirit Photography Portrait', entity_type='skill_generation')`.
3. **Self-check, one retry**: if the composition is cluttered or off-brief, regenerate once with a simpler subject and clearer light.
4. Reply in one or two sentences, e.g. "All set. Your spirit photography portrait is on the canvas. Next I can do man in a dark frock coat." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
Subject: <who/what>. Action: <what they do>. Location: <where>. Composition: <shot size, angle, lens>. Style: an antique late-19th-century spirit photograph: the same adult <apparition: veiled woman (default), man in a dark frock coat, child-sized silhouette, or user-described> standing on a <setting: wooden staircase (default), parlor with floral wallpaper, conservatory with ferns, or user-described>, the figure's lower body fading into a translucent double exposure so the room shows through, sepia-toned albumen print with cracked plate texture, dust specks, vignetting copal varnish edges and faint chemical stains, soft directional window light with a pale bloom around the apparition, <decay: subtle (default), heavy plate damage, or user-described>, fully clothed period dress, unsettling but tasteful. Light: <key light, mood>. No text, no logos.
```

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.

## Examples

**Default**: the user says "this one". Use apparition `veiled woman`, setting `wooden staircase`, 3:4. Reply: "All set. Your spirit photography portrait is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (man in a dark frock coat).
**Thin request**: the user gives one word. Fill the brief from the tuned defaults and generate; do not interrogate.