Low Angle Pose Shot · عوامی Open Skill

Low Angle Pose Shot

Low Angle Pose Shot Digen پر ایک عوامی Open Skill ہے۔ کھولیں اور دیکھیں یہ ورک فلو کیا تخلیق کرتا ہے۔

@BrookeHollis

Custom

1 0 0

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

# Low Angle Pose Shot

Shot from the ground up. The person in your photo is re-posed and captured from a steep low angle — leaning on a wall, knee up or forward lean — for that tall, striking fashion-campaign perspective.

## When to use

- The user wants the person in their photo re-posed and shot from a dramatic low camera angle looking up at them (worm's-eye pose, heroic upward shot, 75-degree low angle)
- A variation on a previous result: one knee raised

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 |
| Pose | No | `forward lean with hands on wall` | forward lean with hands on wall (default), one knee raised, forward lean looking down, or user-described |
| Ratio | No | `3:4 default` | 3:4 default; 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='Low Angle Pose Shot', 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 low angle pose shot is on the canvas. Next I can do one knee raised." 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 photographed from a steep low camera angle about 75 degrees upward, wide 24mm lens near the ground, in <pose: leaning forward with both hands on a wall above the camera (default), standing with one knee raised, forward lean looking down at the lens, or user-described>, same face, hair and outfit, clean bright sky or minimal white architectural ceiling behind, dramatic perspective with long legs and strong foreshortening, crisp fashion-campaign light. <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 "this one" with a photo. Use pose `forward lean with hands on wall`, ratio `3:4 default`, 3:4. Reply: "All set. Your low angle pose shot is on the canvas."
**Variation**: "n