Pet Halloween Costume · skill pública Open Skill

Pet Halloween Costume

Pet Halloween Costume é uma Open Skill pública no Digen. Abra para ver o que este fluxo cria.

@HarperDiaz

Meme

2 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284956/2026-10-17/r4b3735a.webp

# Pet Halloween Costume

Same pet, Halloween-ready. Your pet photo gets a detailed costume with fabric folds and festive props while the face and fur pattern stay unmistakably theirs.

## When to use

- The user wants their pet photo dressed in a detailed Halloween costume while keeping the same pet identity (pet Halloween costume, dog cat costume portrait, holiday pet dress-up)
- A variation on a previous result: vampire cape

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One clear pet face. Ask for another photo if the pet is tiny, blurred or mostly off-frame |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Costume | No | `pumpkin-fairy cape` | pumpkin-fairy cape (default), vampire cape, witch hat, ghost sheet, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 4:5 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='Pet Halloween Costume', 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 pet halloween costume is on the canvas. Next I can do vampire cape." 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 pet from the photo wearing a detailed <costume: pumpkin-fairy cape with a tiny hat (default), vampire cape and bowtie, witch hat and broom accent, ghost sheet with cute eye holes, or user-described>, identity face markings and fur pattern preserved exactly, cozy autumn indoor set with soft string lights, photoreal fur and fabric detail, wholesome non-scary tone. <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 costume `pumpkin-fairy cape`, ratio `3:4 default`, 3:4. Reply: "All set. Your pet halloween costume is on the canvas."
**Variation**: "next variation". Keep the sa