Dark Energy Martial Arts Duel in a Ruined Courtyard
A 15-second cinematic action sequence in which a man with void-black energy erupts from a crater and battles a woman through rotting shoji screens and a stone courtyard. The prompt uses shot-by-shot timecodes, whip-pans, high-speed tracking, and a handheld POV to build a superpowered fight, ending in a massive dark-energy blast.
Prompt (original, unmodified)
**[0s-5s]** Close-up on the man’s face as he lies in the crater; his eyes snap open, glowing with a hollow, void-like black light. He erupts upward in a **violent burst of dark energy**, instantly clearing the smoke. The camera executes a **rapid whip-pan** to follow him as he teleports—appearing as a black blur—behind the woman. She reacts with a spinning back-kick, but he catches her ankle mid-air, the dark energy "corroding" the air around his hand. **[5s-10s]** High-speed tracking shot. The man swings the woman with superhuman force, slamming her through a series of **rotting wooden shoji screens**. The camera follows her through the debris in a single, continuous lateral move. She flips mid-air to recover, but he is already there, delivering a **brutal flurry of palm strikes** infused with black lightning. Each hit creates a localized gravity distortion, warping the light around them. **[10s-15s]** The camera switches to a **shaky, handheld POV** from the woman’s perspective as she is driven back toward a stone lantern. He charges a final, massive sphere of dark energy between his palms and thrusts it forward. The shot cuts to a **wide overhead view** as the courtyard floor shatters completely, the lantern disintegrating into dust. 4K ultra HD, high-contrast lighting, intense particle effects. **Audio:** Distorted electronic screeches, the sound of glass shattering, deep-frequency "void" hums, and a deafening, bass-boosted explosion as the energy connects.
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 AI prompts than in the library overall:
| Technique | In cinematic AI | Library average | Lift |
|---|---|---|---|
| volumetric | 37% | 23% | 1.63x |
| rim light | 16% | 10% | 1.62x |
Across all 5,926 prompts, the techniques used here appear at: tracking 41%, handheld 24%, volumetric 23%, 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.