Plague City Survivors · Open Skill 公开技能
Plague City Survivors
Plague City Survivors 是 Digen 上的公开 Open Skill。打开后即可了解该工作流能制作什么。
Story
0 0 3
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284959/2026-10-17/s3b7xr9h.webp
# Plague City Survivors Empty streets, burning wrecks, ash sky. Your people are dropped into a collapsed plague-era city as weary survivors. ## When to use - The user wants people from their photo placed into a collapsed plague-era city with burning vehicles and empty streets (plague city survivors scene, apocalypse street composite) - A variation on a previous result: ember-warm night Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One or more clear adult faces preferred | | Description | No | tuned default below | What the user wants; merged into the prompt | | Grade | No | `desaturated ash` | desaturated ash (default), ember-warm night, bleak daylight | | Ratio | No | `3:4 default` | 3:4 default; 2:3, 16:9 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='Plague City Survivors', 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 plague city survivors. I can also try ember-warm night 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 people from the uploaded photo composited into a collapsed plague-era city street: abandoned burning vehicles, empty ash-gray avenues, broken windows and distant fire glow, survivor wardrobe accents that stay fully clothed and non-gore, identity faces preserved, cinematic desaturated grade. <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 the style says otherwise, fully clothed, no text unless requested. ``` Quality bar: Name the style's visual traits (medium, brushwork or render, palette, line quality) and apply them to the whole frame; keep the face's likeness readable under the style. ## 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 "use this pic" with a photo. Use grade `desaturated ash`, ratio `3:4 default`, 3:4. Reply: "Done! Here's your plague city survivors." **Variation**: "one more please". Keep the same inputs and change one option (ember-warm night). **Missing input**: no photo was sent. Ask: "I need one clear, front-facing photo to begin. Could you send it?" ## References - `references/image-edit.md`