Cursed Silver-Haired Samurai Girl Battles in Ruined Shrine

A 12-second nonstop cinematic action sequence featuring a cursed female schoolgirl samurai with silver hair and a medical eyepatch, fighting dozens of enemies in an abandoned temple shrine at night. The prompt uses a character reference image to lock identity and appearance, with aggressive tracking shots, whip pans, and blade POV movement following her high-speed katana slashes and shadow energy.

This clip could not be loaded — it may have been removed from X.
Oogie @oggii_0 ·
View on X ↗

Prompt

[Character Reference: image] Strictly follow the reference character's face, long straight silver hair, and the medical eyepatch over her left eye. Do not change identity or facial structure. Fixed appearance: Glowing dark right eye, long silver hair flowing with the wind, a medical eyepatch over the left eye, a torn and slightly bloodstained black school sweater over a white shirt with a bow tie, grey pleated plaid skirt, black knee-high socks and brown loafers, a traditional Japanese katana held in a firm grip, black cursed smoke slowly leaking from the girl's body and the blade, flowing shadow energy aura, calm but cruel expression, supernatural high-speed movement, consistent identity and physical appearance throughout the entire scene. CHARACTER Cursed female schoolgirl samurai, silver-haired warrior, medical eyepatch over left eye, glowing dark right eye, torn black school uniform (sweater and pleated skirt), traditional katana, black cursed smoke leaking from body, shadow energy constantly flowing, calm and ruthless expression, supernatural high-speed movement, consistent identity in all shots. ENVIRONMENT Abandoned temple shrine at night, broken ground, collapsed torii gates, shattered statues, rotten wooden pillars and roof debris scattered around, moonlight entering through broken temple windows, dim stone lantern light contrasting with dark cursed energy, dust and wind moving through the space, dozens of enemies surrounding the samurai girl, dark gritty cinematic atmosphere. CAMERA Aggressive cinematic tracking shots, fast whip pans following slashes, dynamic wide battlefield shots, blade POV movement, smooth high-speed motion tracking, cinematic framing following cursed energy movement, no slow-motion close-ups, continuous fast-paced action camera. CINEMATIC TIMELINE (12s nonstop action) Realistic cinematic multi-shot sequence, epic sci-fi fantasy battlefield, IMAX film simulation, 35mm Panavision lens, f/4 aperture, high dynamic range editing 0-4s The cursed schoolgirl samurai stands in the center of the abandoned temple shrine surrounded by dozens of enemies, black cursed smoke slowly leaking from her body and her katana, wind and dust moving across broken ground, sudden burst into motion as the girl performs an instant iaijutsu draw, her katana unsheathes at extreme speed, dark energy slash wave cuts through multiple enemies at once, camera fast tracking following the slash across the battlefield. 4-8s The girl dashes forward at inhuman speed leaving shadow afterimages, her silver hair fluttering violently as she moves through the enemy ranks, rapid dashes and decapitations, the dark energy from her blade leaving trails of black smoke in the moonlight, cold and ruthless expression visible on her face.
? 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 10s.

What makes this prompt work

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

CAMERA
"pan" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "tracking", "whip pan", "pov".
LIGHTING
"moonlight, low-key" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"dramatic, epic" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 10s, 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