Food Cube Fragments · skill publik Open Skill

Food Cube Fragments

Candy gloss meets a cake caught mid-shatter. I like keeping the real crumb, cream and glaze while one side stays whole. **floor notes:** tips from me: - name your dish, or use the default layered chocolate cream cake - choose half intact and half crumbled for the balanced look - add an adult person photo to preserve the face - set a pale matte neutral backdrop for a clean close-up checklist then go. Post what you make!

@SiennaBrooks

Product

0 1 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284952/2026-10-19/r99rtken.webp

# Food Cube Fragments

A dish frozen mid-shatter. One side stays whole, the other bursts into floating cubes that keep the real crumb, cream and glaze — cinematic, minimal, mouth-watering.

## When to use

- The user wants a food item shown caught halfway between intact and floating 3D cubes (food cube transformation, exploding food cubes, deconstructed dish visual)
- A variation on a previous result: strawberry shortcake slice

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 |
| Food photo | No | — | anchors the dish's exact shape, layers and textures |
| Description | Yes | — | What the user wants; merged into the prompt |
| Dish | No | `layered chocolate cream cake` | layered chocolate cream cake (default), strawberry shortcake slice, glossy glazed donut, or user-described |
| Cube state | No | `half intact and half crumbled into cubes` | half intact and half crumbled into cubes (default), mostly dissolved into cubes, just beginning to crack |
| Backdrop | No | `pale matte neutral` | pale matte neutral (default), soft warm gradient, cool grey studio |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 2:3, 9:16 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='Food Cube Fragments', 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 food cube fragments is on the canvas. Next I can do strawberry shortcake slice." 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 cinematic macro still of <dish: a layered chocolate cream cake (default), a strawberry shortcake slice, a glossy glazed donut, a cheeseburger, or user-described dish> as <state: half intact and half crumbled into floating cubes (default), mostly dissolved into cubes, just beginning to crack, or user-described>, a clean lateral break revealing each layer, loose cubes drifting in mid-air with tiny crumbs and droplets, all shards carrying the food's own textures, ingredients and colors, on a minimalist light matte surface in soft even light, shallow depth of field, studio food photography, sharp detail, no text. <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 i