Paper Cutout Travel Figures

SkillMedia

Turn travel photos with recognizable people into 3:4 posters where real photographed environments contain warm-white paper sketch figures, in split comparison or full-canvas mode.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Paper Cutout Travel Figures skill

What this skill tells your AI

The instructions your AI receives, as published by gz-l/photo-to-poster-skills in skills/paper-cutout-travel-figures/SKILL.md and read by ahel’s review.

Applicability, delivery, and mode selection

  • Use only for photos with recognizable people. If no person is clear enough to preserve, do not add figures; explain that the image is unsuitable.
  • Produce one standalone 3:4 vertical poster per source image. Never combine photos.
  • Offer two modes when the user has not already chosen:
    1. Split comparison — full source photo above, reconstructed real environment with paper figures below.
    2. Full canvas — the whole poster keeps the real environment while all recognizable narrative people become paper figures.
  • Use one mode for all uploaded photos unless the user maps modes per image.
  • Read only the selected guide: split-comparison.md or full-canvas.md.
  • Return a ready-to-use prompt only when explicitly requested; otherwise use the available image generation or editing capability.

Shared visual rules

Preserve each person's identity cues, count, pose, direction, gesture, clothing silhouette, carried objects, spacing, interaction, hand contact, and occlusion, together with architecture, road perspective, materials, natural light, and place atmosphere. A person may leave the composition only through an explicit crop; every recognizable person remaining must match the source count.

Convert narrative people into opaque warm-white thin paper cutouts with restrained fibers, slightly imperfect die-cut edges, loose variable black-ink contours, very few internal sketch lines, and shallow correctly directed layer and foot-contact shadows. Paper figures must stand credibly in the photographed environment with correct scale, perspective, occlusion, ground contact, and light direction. Related bags, hats, cameras, umbrellas, or bicycles may become paper only when essential to the action.

Before rendering, lock source-grounded text: a 1–3-word English title, SCENE NO. XX, and a 5–10-word observation. Never invent relationships, locations, dates, brands, quotations, or attribution; never cover faces, hand interactions, or foot contact.

Avoid

Illustrated environments, transparent photo figures with white-line overlays, cartoon or colored-comic people, cute stickers, speech bubbles, interface graphics, thick foam stickers, altered person counts, invented or duplicated figures, changed poses, separated touching hands, floating people, missing contact shadows, fake text, signatures, handles, logos, and watermarks.

Signals

GitHub stars
21
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
paper-cutout-travel-figures
Source
github.com/gz-l/photo-to-poster-skills