Miniature City Between Fingers · مهارة Open Skill عامة
Miniature City Between Fingers
Miniature City Between Fingers هي Open Skill عامة على Digen. افتحها لتعرف ماذا ينشئ هذا التدفق.
Travel
5 1 5
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284956/2026-10-18/x34tvbtp.webp
# Miniature City Between Fingers An entire city, pinched between two fingertips. Ultra-realistic handcrafted miniature with a raised national flag, a front-and-center landmark and a little engraved name plaque, shot macro with deep focus and soft studio light. ## When to use - The user wants a chosen city and landmark turned into an ultra-realistic handcrafted miniature diorama held between two fingertips (city in miniature, landmark model in hand, souvenir diorama photo) - A variation on a previous result: New York 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 | | City streetscape reference | No | — | refines street-level look, colors and storefronts | | Landmark reference | No | — | refines the landmark's shape and proportions | | Description | Yes | — | What the user wants; merged into the prompt | | City | No | `Paris` | Paris (default), New York, Tokyo, or user-named city | | Landmark | No | `Eiffel Tower` | Eiffel Tower (default), Statue of Liberty, Tokyo Tower, or user-named landmark | | Flag | No | `the city's national flag` | the city's national flag (default), regional contrast flag, or user-described | | Scene | No | `flowered café terraces and cobbled lanes` | flowered café terraces and cobbled lanes (default), riverside promenade, dense old-town roofs with spires, or user-described | | Plaque | No | `engraved brass plate` | engraved brass plate (default), painted enamel sign, or user-described | | Ratio | No | `3:4` | 3:4 (default), 1:1, 16:9, 9:16, or user-described | - 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='Miniature City Between Fingers', 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 miniature city between fingers is on the canvas. Next I can do New York." Results appear on the canvas; never paste URLs. ## Prompt templates **PROMPT** ```text <if photo: The same adult from the reference: <identity line>.> Intentional changes: an ultra-realistic handcrafted miniature diorama of <city: Paris (default), New York, Tokyo, or user-named city> held delicately between two adult fingertips above a plain warm-grey studio surface, a <flag: the city's national flag (default), regional contrast flag, or user-described> on a slim pole rising from the plinth, an instantly recognizable <landmark: Eiffel Tower (default), Statue of Liberty, Tokyo Tower, or user-named landmark> front and center, tiny hand-built <scene: flowered café terraces and cobbled lanes (default), riverside promenade, dense old-town