Samurai Splits Fire Yokai in Burning Village
A cinematic action sequence where a calm samurai faces a massive fire yokai in a burning Japanese village. The samurai charges his katana and delivers a single devastating slash that cuts the yokai in half, ending with embers falling in silence. The prompt uses a shot-by-shot breakdown with dynamic camera work and slow motion.
Prompt (original, unmodified)
An ultra charismatic samurai standing in a burning village, facing a massive fire yokai made of flames and smoke A fire yokai attacks and destroys a village, the samurai steps forward calmly, concentrates energy into his katana, then releases a single devastating slash that cuts the yokai cleanly in half Cinematic dynamic system: wide shot + tracking + close-up + slow motion + impact zoom, clean transitions, no chaos Scene Japanese village on fire, houses burning, flames spreading, embers in the air, night atmosphere Ultra realistic, cinematic, strong fire VFX, high contrast lighting, clear action readability, no distortion 0-2s wide shot village burning fire yokai rampaging, destroying houses 2-4s camera tracking samurai walks forward slowly toward the yokai calm, controlled 4-6s yokai attacks, massive fire strike hits ground explosion of flames 6-8s samurai dodges cleanly fast movement, reappears facing the yokai 8-10s close-up, he stops, grips katana energy begins to build in the blade 10-12s slow motion, fire around him bends away he takes a stance 12-13.5s FINAL ATTACK he performs one fast horizontal slash energy arc travels instantly 13.5-15s IMPACT the yokai freezes for a split second then splits cleanly in two fire collapses and disperses final frame samurai standing still, embers falling silence
Reproduced verbatim from the original post. Never edited or translated. Everything outside this block is our own commentary.
How this prompt compares
The techniques this prompt uses are more common in cinematic realistic prompts than in the library overall:
| Technique | In cinematic realistic | Library average | Lift |
|---|---|---|---|
| low-key | 22% | 17% | 1.31x |
Across all 5,926 prompts, the techniques used here appear at: tracking 41%, close-up 40%, wide shot 26%, low-key 17%.
The 15s duration is not arbitrary: 71% of the prompts in this library that state a duration ask for exactly 15 seconds — Seedance 2.0 accepts clips up to 15 seconds, so 15s is the model's ceiling and the most common choice.