Fragmented FPV Chase of a Cat Through a Parking Garage

An ultra-wide fisheye FPV tracking sequence follows a cat through an abandoned underground parking structure, never fully revealing the animal — only fleeting glimpses of ears, whiskers, paws and fur. Shot at 120fps with continuous focus shifts, exaggerated motion parallax, and a climactic headlight sweep that sends the cat skidding into a spiral before escaping.

This clip could not be loaded — it may have been removed from X.
Sanchit | AI Tools & News @AIwithSanchit ·
View on X ↗

Prompt

Ultra-wide-angle macro FPV tracking sequence following a cat. The feline is never fully revealed; only fragmented glimpses pass the lens: the twitch of an ear, scattered whiskers, a paw brushing the floor, a swath of fur gliding past the camera. Focus continuously shifts between these fleeting details and nearby environmental hazards. Shot at 120fps to capture subtle tremors and high-frequency vibrations as the cat bounds and lands. Setting: An abandoned underground parking structure. Textured concrete floor, numbered pillars with faded, indecipherable markings, shallow puddles and tire tracks reflecting harsh light. Dust particles and condensation mist hang in the air. Sparse cold-white ceiling LEDs mingle with distant vehicle headlights, creating sharp contrast and deep shadows. The cavernous space resonates with emptiness and tension. Movement: The cat navigates unpredictably—darting through narrow gaps, executing sudden 90° pivots, explosive bursts of speed, and tight lateral rolls that skim edges of doors and guardrails. The camera mirrors its frenetic rhythm, micro-vibrating with the steps and accentuating exaggerated motion parallax as pillars and parked cars streak past. Key interaction: A gust of wind—generated by ventilation and a passing car—lifts loose debris: paper scraps, plastic bags, and dust swirl into a spiraling vortex. As the cat rockets forward, debris stretches into radial motion blur lines, enhanced by fisheye distortion. A rolling tire splashes a puddle, scattering droplets that refract light realistically. Climactic moment: A car’s headlight suddenly sweeps across the scene, reflecting sharply off the wet floor. The cat skids into a chaotic spiral, claws gripping the slick surface, fur vibrating, droplets flinging outward—captured in 120fps slow motion. Motion instantly resumes at high speed as the cat races along the ramp edge, hugging walls, and threads through a half-open maintenance door or narrow fence gap, escaping into safety. Atmosphere: Claustrophobic, urgent, and tense, yet ultimately triumphant. Sound design emphasizes rushing air, splashing water, metallic echoes from guardrails, and residual vibrations. The sequence concludes as the cat lands in a shadowy corner, with the camera’s lingering tremors gradually fading into stillness.
? 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 15s.

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: "macro", "slow motion".
LIGHTING
"low-key, practical lights" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"tense, energetic" — 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.
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