geminiprompts.world

anime fantasy Seedance 2.0 prompt

Chibi Plush Mascots in Continuous Anime Flythrough

A continuous, cut-free anime opening sequence flying through an infinite deep blue void where four chibi plush animal mascots appear along the route. It uses fast forward dolly movement with lateral drifts, speed ramping, and high animation density in a dark fantasy cel-shaded style.

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

Maki@Sunwood AI Labs. @hAru_mAki_ch · Original post: Apr 12, 2026

Prompt

Full-color Japanese anime. Fast camera movement, strong speed ramping, high animation density, a 24 FPS anime opening. A viewpoint darting left and right, with dynamic poses.

type: anime_opening_continuous_camera_flythrough

style: dark fantasy anime, cel-shaded 2D, high contrast; characters use the attached tiled baby plush mascot design: SD/chibi, pastel storybook look, fluffy texture, big eyes, rosy cheeks, pacifiers, animal hoods

characters:
  $ A:
    ref: attached tiled baby plush character sheet
    design: lion baby plush mascot, regal
  $ B:
    ref: attached tiled baby plush character sheet
    design: bear baby plush mascot, brave
  $ C:
    ref: attached tiled baby plush character sheet
    design: rabbit baby plush mascot, mysterious
  $ D:
    ref: attached tiled baby plush character sheet
    design: fox baby plush mascot, sly

concept: >
  One continuous camera move through a blue void.
  Characters appear along the route. No cuts.

camera: fast forward dolly with lateral drifts, rollercoaster POV, nonstop

environment:
  space: infinite deep blue void, drifting white petals and feathers, diagonal blades and ribbons near lens
  palette: deep crimson (# 5A0000–# 8B0000), cyan mint accents, black shadows
  lighting: dramatic rim light, deep shadows

path:
  - subject: $ A
    pose: on a throne, lion plush baby, regal, magic aura
    framing: push-in close-up, drift past shoulder

  - subject: $ B
    pose: mid-lunge with enchanted blade, bear plush baby, action energy
    framing: quick arc around him

  - subject: $ C
    pose: katana vertical, eyes over steel, rabbit plush baby, quiet intensity
    framing: lateral drift past the blade

  - subject: $ D
    pose: shh gesture, blade tip foreground, fox plush baby, sly tension
    framing: low angle, slow final push-in, camera rests

foreground_wipes: diagonal blades, petals, feathers, ribbons passing close to lens
negative: hard cuts, static camera, fades, text, photorealism, realistic adult proportions, gritty realism

? 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	dolly · static/fixed · pov · close-up
Lighting	rim light · dramatic lighting · low-key
Mood	energetic · dramatic
Aspect ratio	9:16
Difficulty	intermediate
Model	Seedance 2.0
Prompt language	English
Includes	Not specified

Categories

Filter by technique

dolly static/fixed pov close-up rim light dramatic lighting low-key energetic dramatic

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 →

CAMERA: "dolly" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "static/fixed", "pov", "close-up".
LIGHTING: "rim light, dramatic lighting, low-key" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD: "energetic, dramatic" — 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.