Halloween Pet Costume · Open Skill 공개 스킬

Halloween Pet Costume

Halloween Pet Costume은 Digen의 공개 Open Skill입니다. 열어 보면 이 워크플로가 무엇을 만드는지 알 수 있습니다.

@CalebMonroe

Meme

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284955/2026-10-16/cc838wsx.webp

# Halloween Pet Costume

Spooky and cute. Your pet gets a Halloween costume picked to suit its species, breed and personality, in a photorealistic portrait with glowing pumpkins and a full moon.

## When to use

- The user wants their pet photo turned into a Halloween costume portrait (pet in vampire, witch, superhero or pumpkin costume)
- A variation on a previous result: vampire

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 |
| Costume | No | `auto-picked` | auto-picked (default), vampire, witch, superhero, pumpkin, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 2:3, 9:16, 16:9 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 Pet 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. "Your halloween pet costume is ready. Want another take with vampire?" 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 in a Halloween costume chosen to suit its species, breed, size and personality (vampire cape, witch hat, superhero, pumpkin, or one the user names), photorealistic spooky-cute Halloween portrait with glowing jack-o'-lanterns, autumn leaves and a full moon, preserve the pet's unique markings and features. <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 "here's my selfie, do it" with a photo. Use costume `auto-picked`, ratio `3:4 default`, 3:4. Reply: "Your halloween pet costume is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (vampire).
**Missing input**: no photo was sent. Ask: "Send one clear photo where your face is easy to see, and I'll start."

## References

- `r