Collectible Plush Maker · publiczny skill Open Skill

Collectible Plush Maker

hook: I make collectible plushes with oversized heads and embroidered features. The head does the talking. Send an adult photo, character reference, or description. Get a realistic plush with fuzzy fabric and visible stitching. tips: Choose sitting, standing, or waving; use 3:4 by default, or request 1:1 or 4:5.

@TylerHayes

Product

3 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284953/2026-10-16/rrqqwzdk.webp

# Collectible Plush Maker

Soft, squishy and unmistakably them. Any character becomes a realistic collectible plush with an oversized head, stubby limbs, fuzzy fabric, visible stitching and embroidered features.

## When to use

- The user wants a character turned into a realistic collectible plush toy (big-head plushie, stuffed toy version, embroidered plush figure)
- A variation on a previous result: standing

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Person photo | No | — | Optional; if given, the face is preserved |
| Character reference | No | — | picture of the character whose markings and accessories should carry over |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Pose | No | `sitting` | sitting (default), standing, or waving |
| 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. Fill the template below from the user's description. Use the tuned defaults for anything they leave out; ask one short question only if the subject itself is unclear.
3. If a person photo is given: `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.')` and add the identity clause.
4. With reference images: `generate_image(prompt=<PROMPT>, input_urls=[refs...], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Collectible Plush Maker', entity_type='skill_generation')`; without: the same call with `model='t2i.hd'` and no `input_urls`.
5. **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.
6. Reply in one or two sentences, e.g. "All set. Your collectible plush maker is on the canvas. Next I can do standing." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
<if photo: The same adult from the reference: <identity line>.> Intentional changes: a realistic product photo of a collectible plush toy of <character: from the character reference if given, else the user's description>, oversized head, tiny rounded body and stubby limbs, soft fuzzy minky fabric with visible seams and stitching, embroidered eyes, brows and mouth showing <expression: a happy smile (default) or user-described>, the character's signature colors, markings and key accessories recreated in felt and fabric, <pose: sitting upright (default) or standing>, soft studio light with gentle shadows on a neutral warm-gray backdrop, tactile macro detail of fibers, premium collectible packaging-shoot quality, it remains a plush toy. <user details and options>. Clear focal hierarchy; any text short, in quotes and spelled exactly; no real brands. 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: Keep on-image text short and in quotes; no real brand names or logos; one clear focal hierarchy.

## 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