Landmark Street Grid Nine · Open Skill 공개 스킬
Landmark Street Grid Nine
Landmark Street Grid Nine은 Digen의 공개 Open Skill입니다. 열어 보면 이 워크플로가 무엇을 만드는지 알 수 있습니다.
Travel
1 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321671/2026-10-21/3a58bhvw.webp
# Landmark Street Grid Nine One face, nine frames, one global landmark. The woman in your photo becomes the subject of a 3x3 wide-angle street shoot at a famous monument — same face, same styling, different poses and angles in every tile. ## When to use - The user wants a 3x3 photo grid of the same adult person shot in wide-angle street style at a famous landmark (landmark photo grid, nine-panel travel shoot, character-consistent city grid) - A variation on a previous result: golden-hour daylight Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult woman, face clear; head-and-shoulders or full body works. Ask for another photo if the face is tiny, blurred, hidden, or if the person may be under 18 | | Description | No | tuned default below | What the user wants; merged into the prompt | | Look | No | `neon night street` | neon night street (default), golden-hour daylight, rainy blue-hour reflections, or user-described | | Landmark | No | `Eiffel Tower at night` | Eiffel Tower at night (default), Shibuya crossing, Times Square, Tower Bridge, or user-named landmark | | Outfit | No | `black tailored coat with slim boots` | black tailored coat with slim boots (default), casual streetwear, elegant long dress, or user-described | | Ratio | No | `3:4 default` | 3:4 default; 1:1, 9:16, 2:3 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. **Identity read**: `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.')`. 3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Landmark Street Grid Nine', entity_type='skill_generation')`. Merge the user's details and options into the template. 4. **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. 5. Reply in one or two sentences, e.g. "Done! Here's your landmark street grid nine. I can also try golden-hour daylight if you like." Results appear on the canvas; never paste URLs. ## Prompt templates **PROMPT** ```text The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: the same adult woman kept character-consistent through all nine panels, shot as a 3x3 grid of wide-angle street photographs at <landmark: Eiffel Tower at night (default), Shibuya crossing, Times Square, Tower Bridge, or user-named landmark> in <look: neon night street (default), golden-hour daylight, rainy blue-hour reflections, or user-described>; she wears <outfit: black tailored coat with slim boots (default), casual streetwear, elegant long dress, or user-described>, mostly three-quarter or full body, low wide-angle lens drama, each tile a different pose and camera distance against the monument, glossy reflective pavement and city lights, crisp editorial travel-photography realism, fully clothed. <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 suit