geminiprompts.world

anime stop motion slow push-in Seedance 2.0 prompt

Paper-Puppet Horror at a Night Bus Stop

A 15-second vertical horror animation in a flat paper-puppet style with rough textures, dark muted colors, and slight projector flicker. The first cut shows a young woman alone at a Japanese bus stop at night under a flickering streetlight, with a slow push-in.

This clip could not be loaded — it may have been removed from X.

トーマ＠Grok愛好家 @TomaAIbijo · Original post: Apr 7, 2026

Prompt

Scene 1
horror animation. Flat paper-puppet look, rough textures, dark muted colors, slight projector flicker. 15-second vertical video (9:16), 5 cuts.

Cut1 (0-3s)
Night Japanese street, flickering streetlight. Young woman alone at bus stop. Paper cut-out style, slow push-in.

? How to use this prompt ▾

Copy the prompt using the green "Copy prompt" button above.
Open your model — launch Seedance 2.0 on its official interface.
Paste & generate — keep the verbatim prompt text for best adherence. Set aspect ratio to 9:16 and clip duration to 15s.

Spec sheet

Duration	15s
Camera	Not specified
Lighting	low-key
Mood	eerie
Aspect ratio	9:16
Difficulty	intermediate
Model	Seedance 2.0
Prompt language	English
Includes	Not specified

Categories

anime stop motion slow push-in

Filter by technique

Filter thousands of prompts by camera movement, lighting, duration, aspect ratio and category.

Browse complete prompt library →

What makes this prompt work

Every insight below is verified against benchmark generation parameters, not asserted. How our prompt engineering benchmarks work →

LIGHTING: "low-key" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD: "eerie" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION: At 15s, this clip is optimized for high temporal coherence and fluid, realistic motion physics.
MODEL: Seedance 2.0 (ByteDance) provides the underlying diffusion and motion architecture. Camera, lighting and duration cues transfer across models — what differs is how literally each model interprets motion.
PROMPT LANGUAGE: The prompt is written in English. This library keeps every prompt in its original language rather than translating it — the exact words are what was conditioned during generation.