Selective Color Street Style · Open Skill 公開スキル
Selective Color Street Style
Ask: After-hours crosswalk. One color stays, rest goes gray. What do I type? Get: Scene plus outfit. Say adult photo, crosswalk, sunglasses, clutch. Keep it plain. Ask: Which photos are required? Get: Description is required. Woman and outfit photos optional. Text alone can run. Ask: What ratio should I pick? Get: 3:4 portrait default. 2:3, 9:16, 1:1 also. Change accent or outfit first.
TryOn
1 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/ykw6zs3v.webp
# Selective Color Street Style A monochrome crosswalk, a confident stride, and a single bright color on the top, sunglasses and clutch. ## When to use - The user wants a street fashion photo in black and white with one vivid accent color (selective color fashion, crosswalk editorial) - A variation on a previous result: 2:3 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 | | Woman photo | No | — | identity | | Outfit photo | No | — | the ensemble | | Description | Yes | — | What the user wants; merged into the prompt | | Ratio | No | `3:4 default` | 3:4 default; 2:3, 9:16, 1:1 | - 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='Selective Color Street Style', 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 selective color street style is on the canvas. Next I can do 2:3." 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 crisp street-fashion photograph on a black-and-white city crosswalk, the woman mid-stride in a tailored look; only the top, sunglasses and clutch keep one bright <accent color>. <user details and options>. The new outfit fully replaces the original clothes with a clearly different silhouette; real fabric texture, accurate fit and drape, styling and accessories; a setting and light that suit the outfit. 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: Make the new outfit read as real fabric: bold silhouette change from the original clothes, named materials and textures, hero lighting, and a scene that suits the outfit (not the selfie background). ## 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 ratio `3:4 default`, 3:4. Reply: "All set. Your selective color street style is on the canvas." **Variation**: "next variation". Keep the same inputs and change one option (2:3). **Thin request**: the user gives one word. Fill the brief from the tuned defaults and generate; do not interrogate. ## References - `references/image-edit.md`