Anime Girl Parkour Rooftop Gameplay Cinematic

A 15-second anime-style gameplay cinematic of a silver-haired girl performing parkour across red rooftops in a futuristic Tokyo-inspired city. The prompt specifies a third-person follow camera with handheld motion, slow-motion mid-air jumps, and on-screen game HUD elements like a mini-map and health bar.

This clip could not be loaded — it may have been removed from X.
Anissa @SimplyAnnisa ·
View on X ↗

Prompt

Create a 15-second ultra-smooth anime-style gameplay cinematic inspired by a futuristic Japanese city exploration game.
A young anime girl character with white/silver hair, wearing a stylish black-and-white futuristic outfit with short skirt, thigh-high socks, and combat-style shoes, is running and climbing across red rooftop houses in a dense modern Tokyo-inspired city.
Environment:
Bright sunny daytime, blue sky with soft clouds, realistic anime lighting, modern skyscrapers in background, cherry blossom trees near houses, urban Japanese neighborhood mixed with futuristic city towers. Rooftops have realistic red metal textures with sunlight reflections.
Character movement:
Fast agile parkour movement across rooftops.
Smooth running → jump → wall climb → rooftop landing.
Natural anime body physics, cloth movement, hair bounce, accurate foot placement.
Movement should feel like real gameplay captured live from a AAA anime open-world action game.
Camera style:
Third-person gameplay camera positioned slightly behind character.
Dynamic camera follow with slight handheld motion.
Smooth tracking movement.
Minor motion blur during jumps.
Game HUD/UI visible on screen like a real anime action RPG.
Mini-map top left, action buttons on right side, health/stamina bar bottom center.
Sequence:
0–4s
Character runs across rooftop while camera follows behind smoothly.
4–8s
She jumps between rooftops with cinematic slow-motion mid-air moment.
8–12s
Character grabs edge of higher rooftop and climbs upward naturally.
12–15s
Wide gameplay shot showing futuristic city skyline behind her while she stops briefly on rooftop edge. Wind moves hair and clothes naturally.
Style & Quality:
Ultra detailed anime rendering, high-end cel shading mixed with realistic lighting, smooth gameplay animation, modern gacha game aesthetic, polished textures, soft bloom, sharp shadows, immersive open-world atmosphere, 60fps feeling, cinematic gameplay trailer quality.
Negative Prompt:
low quality, broken anatomy, floating body, extra limbs, blurry textures, bad hands, static camera, unrealistic movement, low fps, distorted face, glitch effects, ugly lighting, oversaturated colors, missing UI, stiff animation.
? How to use this prompt ▾
  1. Copy the prompt using the green "Copy prompt" button above.
  2. Open your model — launch Seedance 2.0 on its official interface.
  3. Paste & generate — keep the verbatim prompt text for best adherence. Set aspect ratio to 9:16 and clip duration to 17s.

What makes this prompt work

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

CAMERA
"tracking" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "handheld", "static/fixed", "slow motion".
LIGHTING
"natural light" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"energetic, cinematic" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 17s, 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.
Seedance 2.5 BytePlus Cloud Partner

Tell bigger stories with Seedance 2.5

Create AI videos up to 30 seconds long with richer image, video, and audio references. Ideal for complex ideas that need consistency and control.

Explore on BytePlus Official ByteDance Enterprise Cloud