Snow Sculpture Object — Open Skill

Snow Sculpture Object

Q: The stairwell had one snow object. I made the object. A: Ask for a description. Add an object photo if you need its geometry. Q: Get a sculpture from that? A: Get the object sculpted entirely from fresh white snow, half sunk into a snowy surface and shot straight from above. Q: What format should I use? A: Get 3:4 portrait. Every generation stays portrait, even when the photo is wider.

@MayaCalloway

Poster

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/c9tgzjbq.webp

# Snow Sculpture Object

Any object you name, sculpted entirely from fresh snow and half sunk into a snowy surface, shot from straight above.

## When to use

- The user wants an object recreated as a sculpture made of white snow, seen from above
- A variation on a previous result: a different layout

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 |
| Object photo | No | — | geometry |
| Description | Yes | — | What the user wants; merged into the prompt |
| Orientation | No | `3:4` portrait | Other ratios 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='Snow Sculpture Object', 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 snow sculpture object is on the canvas. Next I can do a different layout." 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 top-down photo of <object> sculpted entirely from voluminous white snow, slightly sunken into a snowy surface, realistic highlights and soft shadows. <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 says "this one". Use the tuned defaults, 3:4. Reply: "All set. Your snow sculpture object is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (a different layout).
**Thin request**: the user gives one word. Fill the brief from the tuned defaults and generate; do not interrogate.

## References

- `references/image-edit.md`