Tiny Store Street Scene · Open Skill 공개 스킬
Tiny Store Street Scene
Tiny Store Street Scene은 Digen의 공개 Open Skill입니다. 열어 보면 이 워크플로가 무엇을 만드는지 알 수 있습니다.
Other
0 2 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284959/2026-10-19/4ansshm2.webp
# Tiny Store Street Scene Your brand, one whole dollhouse street. A toy-scale shop with a working awning and packed window display sits in a busy sunlit block, seen from above as if you're drifting in over the rooftops. ## When to use - The user wants a playful miniature-brand storefront built into a lively city street and seen from above (tiny shop street, miniature storefront scene, dollhouse-city shop view) - A variation on a previous result: a bakery 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 | | Brand asset | No | — | logo or wordmark that appears on the signage and window decals; default none - the shop gets a clean imagined wordmark | | Storefront reference | No | — | the real facade whose architecture and window layout is echoed; default none - a generic toy-scale corner facade | | Merchandise reference | No | — | product packaging that stocks the window display; default none - imagined goods | | Description | Yes | — | What the user wants; merged into the prompt | | Store | No | `a specialty coffee shop` | a specialty coffee shop (default), a bakery, a flower shop, a bookstore, or user-described | | Brand placement | No | `awning and main sign` | awning and main sign (default), window decal, hanging blade sign | | 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='Tiny Store Street Scene', 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 tiny store street scene. I can also try a bakery 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 charming miniature storefront for <store: a specialty coffee shop (default), a bakery, a flower shop, a bookstore, or user-described> at toy scale, set into a lively sunlit city street with tiny anonymous pedestrians, a parked taxi and street trees, seen from a high three-quarter aerial angle with a gentle sweeping approach toward the storefront; the awning, hanging sign and main window display carry the <brand: the supplied logo (default) or a clean imagined wordmark>; the stocked windows show <merchandise: the supplied products (default) or imagined goods>, warm afternoon light, shallow depth of field, crisp diorama detail, no real-world logos beyond the user's own, no human subject to preserve. <user details and options>. Apply the style to the entire frame wit