Cloud Shape Landscape · সর্বজনীন Open Skill

Cloud Shape Landscape

Cloud Shape Landscape Digen-এ একটি সর্বজনীন Open Skill। খুলে দেখুন এই ওয়ার্কফ্লো কী তৈরি করে।

@NateSullivan

Custom

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284959/2026-10-18/h2sj8vxe.webp

# Cloud Shape Landscape

Look up — the sky has drawn your object. A soft, fluffy cloud takes its clear silhouette above calm, sunlit country.

## When to use

- The user wants an object formed out of soft realistic clouds floating above a peaceful landscape (cloud silhouette art, object-shaped cloud photo, sky sculpture)
- A variation on a previous result: mountain lake

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 |
| Shape object | No | — | the object the cloud outline follows |
| Landscape place | No | — | the scenery below |
| Description | Yes | — | What the user wants; merged into the prompt |
| Setting | No | `rolling green meadows` | rolling green meadows (default), mountain lake, coastal cliffs, lavender fields, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 16:9, 1:1 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='Cloud Shape Landscape', 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. "Done! Here's your cloud shape landscape. I can also try mountain lake if you like." 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 landscape photograph with one clearly recognizable cloud formation shaped like <object: a teapot (default) or the user's object/reference> drifting high above <setting: rolling green meadows (default) or the place reference/description>; the shape is formed organically from soft volumetric cloud with wispy edges and sunlit tops, not a solid object, blue sky depth, gentle natural light, peaceful wide composition. <user details and options>. Professional composition, deliberate lens and light, rich environmental detail. 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: Give the shot a full brief: subject, action, location, composition, lens and light. Never leave a thin one-line prompt.

## 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 "use this pic". Use setting `rolling green meadows`, ratio `3:4 default`, 3:4. Reply: "Done! Here's your cloud shape landscape."
**Variation**: "one more please". Keep the same inputs