Clay Landmark World · skill Open Skill công khai
Clay Landmark World
Clay Landmark World là một Open Skill công khai trên Digen. Mở ra để xem workflow này tạo gì.
ArchViz
0 1 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284958/2026-10-19/39zbqmjk.webp
# Clay Landmark World Whole cities squeezed into thumb-sized clay. Your landmark and its neighborhood get sculpted in bright modeling clay — visible fingerprints, soft rounded towers, a toy-sized river — as one wide, sculptural, text-free little world. ## When to use - The user wants a landmark and its surroundings rebuilt as a miniature world made of colorful modeling clay (clay landmark diorama, plasticine city world, handmade clay miniature) - A variation on a previous result: Big Ben 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 | — | architecture and spatial layout are kept recognizable | | Description | No | tuned default below | What the user wants; merged into the prompt | | Landmark | No | `Eiffel Tower` | Eiffel Tower (default), Big Ben, Colosseum, Sydney Opera House, or user-named | | Clay finish | No | `soft matte plasticine` | soft matte plasticine (default), glossy glazed clay, or rougher hand-pressed clay | | Detail level | No | `full miniature neighborhood` | full miniature neighborhood (default), landmark only on a clay plinth, or extra-tiny town around it | | Ratio | No | `3:4 default` | 3:4 default; 1:1, 16:9, 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='Clay Landmark World', 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 clay landmark world is on the canvas. Next I can do Big Ben." 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 whimsical miniature world sculpted entirely from colorful modeling clay, centered on <landmark: Eiffel Tower (default), Big Ben, Colosseum, Sydney Opera House, or user-named landmark> rebuilt from its reference photo with recognizable architecture and spatial layout: soft rounded clay towers, bridges and rooftops with visible fingerprints and thumb-pressed edges, a river of swirled blue clay, bottle-green clay trees, tiny clay boats and figures on the banks, puffy white clay clouds in a saturated blue sky, wide three-quarter view over the whole scene, bright plasticine toy lighting, handmade sculptural look, no lettering anywhere. <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