Landmark Miniature Cloud Title · Open Skill 公开技能

Landmark Miniature Cloud Title

Q: Ask: I have a city and maybe one landmark photo. What do I send? A: Get: Send a description. A landmark photo is optional, but useful for the subject. Q: Ask: What comes back? A: Get: A detailed miniature landmark district in tilt-shift focus, with the city name written above it in white vapor. Q: Ask: Does it need landscape framing? A: Get: No. I make it portrait, 3:4, for the after-hours city-poster look. Keep the description specific.

@MayaCalloway

Travel

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/r9suq9w4.webp

# Landmark Miniature Cloud Title

A whole landmark district as a handmade miniature in tilt-shift focus, with the city's name written above it in white vapor.

## When to use

- The user wants a city promo visual of its landmark as a detailed miniature with the city name written in clouds (tilt-shift city poster)
- A variation on a previous result: a stronger style intensity

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 |
| Landmark photo | No | — | Reference image |
| 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='Landmark Miniature Cloud Title', 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 landmark miniature cloud title is on the canvas. Next I can do a stronger style intensity." 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 city promotional visual: the most recognizable landmark area of <city> as a highly detailed physical miniature with tilt-shift focus, strong natural side sunlight, the city name written in readable white vapor clouds above, a subtle national flag. <user details and options>. Apply the style to the entire frame with its signature traits (medium, texture, palette, linework); the person stays recognizable under the style. 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: Name the style's visual traits (medium, brushwork or render, palette, line quality) and apply them to the whole frame; keep the face's likeness readable under the style.

## 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 landmark miniature cloud title is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (a stronger style intensity).
**Thin request**: the user gives one word. Fill the brief from the tuned defaults and generate; do not interrogate.

## References

- `references/image-edit.md`