openmotion-paper-diorama
OpenMotion — Turn a history or process story into layered cut-paper diorama scenes with a slow camera push between paper planes. Use for history lessons, how-it-was-made stories and cultural explainers.
Try your first task
A source-grounded starter task has not been verified for this skill yet.
SKILL.md
name: openmotion-paper-dioramadescription: >- OpenMotion — Turn a history or process story into layered cut-paper diorama scenes with a slow camera push between paper planes. Use for history lessons, how-it-was-made stories and cultural explainers.OpenMotion · Paper Diorama
Build the video as a native OpenMotion HTML/CSS/JS composition through the installed OpenMotion production Skill: create or open the project, author the composition, save with revision protection and preview. This library Skill adds creative direction only; it registers no MCP Tool or production route. Treat palette, font and timing values below as starting points; a supplied Brandkit or the user's brand wins. For missing images, voice or music, first discover providers and model IDs with openmotion_media_use, then generate with openmotion_assets_use; get the user's consent before any paid generation. Never invent quotes, numbers, specs or dates.
Status: recipe / draft. No executable template or rendered comparison yet.
Use for: history lessons, craft and process stories, short cultural explainers narrated by a voice.
Look
| Element | Starting value |
|---|---|
| Planes | 4–6 flat paper layers per scene (sky, far hills, mid buildings, near water, foreground prop), each with a soft drop shadow, 0 10px 8px at 35% black |
| Palette | Warm dusk set: sky #E58E5A to #F6DDB2, sea #2C5466, hills #7C918F, buildings #C9A27E / #B9805F; night shifts the sky to #1E2F4C |
| Texture | Fine paper grain over everything (fractal noise, multiply, about 30%) |
| Type | One display serif for chapter titles on a torn paper label, a small spaced sans kicker for era or chapter |
Motion
- Open each scene as a pop-up: layers rise into place back to front, 280 ms apart, with a slight overshoot (700–1000 ms each).
- Move the camera slowly (6–8% push over the whole scene); nearer layers move more than far ones.
- Show change through light, not cuts: sky darkens over 2–3 s, windows switch on one by one at random 100–250 ms gaps.
- Hold each finished scene at least 1.5 s before the next pop-up.
Inputs
Required: the narration script or topic, 3–6 key moments to stage, and the facts or dates to show. Optional: reference photos of the place or object, voice-over, music. Generated pieces go through openmotion_media_use then openmotion_assets_use; one test scene is approved before batch generation. Label generated people as generated.
Avoid
Photo textures inside layers, more than one moving prop at a time, dates or numbers the brief does not supply.
Review
No empty layer edges during the push; the label reads at 1× speed; one focal point per scene; light changes land on their narration line.
Provenance
Written for OpenMotion after surveying publicly listed workflow names and descriptions in ChatCut's preset gallery (November 2026). Original text; no ChatCut prompts, source code, templates or media are included. Apache-2.0, like the rest of the repository.