2D Anime Girl Parkour Through Live-Action Japanese Coastal Town

A 15-second, 8-cut parkour sequence in which a 2D anime character sprints, flips, and rolls across a photorealistic Japanese seaside town, from promenade to seawalls and breakwaters. The prompt locks the character's face, hair, and costume across every cut while blending 2D anime style with live-action coastal backgrounds. It specifies shot-by-shot camera angles, timing, and a sunset hero climax.

This clip could not be loaded — it may have been removed from X.
アユネオ @Ayu_AI_0912 ·
View on X ↗

Prompt

15-second cinematic parkour action video, 16:9, 1080p, 8 hard cuts. The protagonist is the 2D anime character from image . Her face, hairstyle, costume, and all character features must be preserved exactly in every cut. The 2D anime-style character coexists naturally within a live-action photorealistic real-world coastal Japanese town environment. Setting: real contemporary Japanese seaside town — coastal promenade, harbor walkways, seawalls, concrete breakwaters, wooden boardwalks, fishing port streets, beachside stairs, waterfront railings, piers, marina structures, coastal buildings, ocean views, and distant islands typical of Yokohama Bay, Enoshima, Atami, or Kobe waterfront. Natural daylight or golden-hour coastal lighting.

Shot 1 [00:00–00:01.20]: Low rear 3/4 tracking shot, ground-level camera nearly scraping the pavement of a seaside promenade. Protagonist crouches then explodes into a sprint toward a low concrete seawall. Camera follows close behind.

Shot 2 [00:01.20–00:03.60]: Front 3/4 low-angle follow shot. Protagonist launches into a forward flip over the first seawall. At peak, full body clears the obstacle. Cinematic framing against the ocean and coastal buildings. Shallow depth of field.

Shot 3 [00:03.60–00:04.93]: True side close shot near ground. Landing flows seamlessly into a running forward roll along the promenade — shoulder-to-back weight transfer, rises immediately. Full body in frame.

Shot 4 [00:04.93–00:07.33]: Opposite low side angle on a waterfront observation deck. Protagonist accelerates and launches a large forward flip over a concrete seawall. Ocean horizon fills the background.

Shot 5 [00:07.33–00:08.67]: Near-overhead bird's-eye shot. Protagonist lands and rolls along the coastal walkway. Harbor, piers, and waterfront scenery visible around her. Body stays on surface.

Shot 6 [00:08.67–00:11.07]: Retreating front-facing follow camera. Protagonist charges a waterfront staircase railing or concrete breakwater barrier, forward flip captured from the front. Camera retreats with slight handheld shake.

Shot 7 [00:11.07–00:12.40]: Rear diagonal close tracking. Quick forward roll then sprint toward the final seawall obstacle. Low camera, handheld feel, protagonist fully in frame.

Shot 8 [00:12.40–00:15.00]: Hero climax shot. Maximum-height forward flip over a large concrete breakwater against the sunset ocean skyline. Camera arcs from front 3/4 to opposite side during rotation. Protagonist lands and runs powerfully out of frame.

Global rules: No T-poses, no teleportation, no body penetrating obstacles. Character appearance identical in every cut. 2D anime character style preserved against fully live-action photorealistic coastal Japanese town background.
? 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 16:9 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: "handheld", "low-angle", "overhead".
LIGHTING
"golden hour, 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 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