Stairway Back View · skill Open Skill công khai

Stairway Back View

Stairway Back View là một Open Skill công khai trên Digen. Mở ra để xem workflow này tạo gì.

@BrookeHollis

Custom

2 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284958/2026-10-16/rgwra2qp.webp

# Stairway Back View

Walk away in style. Even from a front-facing photo, you get a cinematic rear view climbing a staircase, outfit and hair kept, with depth and light pulling the eye upward.

## When to use

- The user wants a rear-view photo of themselves walking up a staircase, even from a front-facing photo (back view climbing stairs, walking-away stair shot)
- A variation on a previous result: modern concrete

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult with the face clearly visible. Ask for another photo if the face is tiny, blurred, heavily covered or in profile |
| Staircase | No | `sunlit stone steps` | sunlit stone steps (default), modern concrete, spiral, grand indoor, or user-described |
| Ratio | No | `9:16 default` | 9:16 default; 3:4, 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='9:16', name='Stairway Back View', 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. "All set. Your stairway back view is on the canvas. Next I can do modern concrete." 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 seen from behind climbing a long staircase mid-step, one foot on the next stair and a hand lightly on the rail, same outfit, hair and body shape as the reference reconstructed from the back, the stairs leading upward into soft light, strong leading lines and depth, low camera a few steps below, natural daylight, photoreal. <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 9:16. 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 "this one" with a photo. Use staircase `sunlit stone steps`, ratio `9:16 default`, 9:16. Reply: "All set. Your stairway back view is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (modern concrete).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References