Worm's-Eye Ultra-Wide · publiczny skill Open Skill
Worm's-Eye Ultra-Wide
Worm's-Eye Ultra-Wide to publiczny Open Skill w Digen. Otwórz go, by zobaczyć, co tworzy ten workflow.
Custom
3 1 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284955/2026-10-16/z4kkhcc4.webp
# Worm's-Eye Ultra-Wide Lens on the floor, you in the sky. Your photo is re-shot from ground level with an extreme ultra-wide lens: boots huge in the foreground, you towering overhead, and the whole world bending dramatically around you. ## When to use - The user wants their photo re-shot from ground level with an extreme ultra-wide lens so they tower over the scene (worm's-eye full-body shot, 14mm ground-up perspective, giant-scale fashion angle) - A variation on a previous result: moonlit Halloween pumpkin forest Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult, ideally full-body or three-quarter so the outfit and shoes can be kept. Ask for another photo if the face is tiny, blurred or hidden | | Description | No | tuned default below | What the user wants; merged into the prompt | | Setting | No | `original scene widened` | original scene widened (default), moonlit Halloween pumpkin forest, neon city street at night, 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='Worm's-Eye Ultra-Wide', 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. "Your worm's-eye ultra-wide is ready. Want another take with moonlit Halloween pumpkin forest?" 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 in the same outfit re-photographed full-body from an extreme worm's-eye angle with a 14mm ultra-wide lens placed on the ground between their feet, shoes large and sharp in the foreground, legs and body rising in strong converging perspective, face clearly visible looking down toward the lens with a confident expression, the setting expanded around them into a towering wide environment (<setting: their original scene widened and dramatized (default), moonlit Halloween pumpkin forest, neon city street at night, or user-described>), sky and tall elements bending inward at the frame edges, dramatic rim light and volumetric atmosphere, crisp edge-to-edge detail, photoreal campaign photography, 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 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 u