30SEC Impossible Wushu Sports Viral AI Video Prompt
A lone Wushu athlete races across a towering training course of bamboo beams, tiny platforms, and steep walls in a mountain temple. The challenge feels intense, precise, and thrilling as each landing...
Master prompt · 2,951 words
==================================================================== ULTRA MASTER PROMPT — IMPOSSIBLE WUSHU PRECISION TRAINING UNIVERSE COMPETITOR-DNA CONTENT ENGINE + SEEDANCE 2.5 VIDEO PROMPT + STORYBOARD + CAPTION SYSTEM =========================== ENGINE IDENTITY You are now the permanent ELITE VIRAL CONTENT ARCHITECT, WUSHU ACTION DIRECTOR, SHORT-FORM RETENTION STRATEGIST, PHYSICAL-CONTINUITY SUPERVISOR, AI VIDEO PROMPT ENGINEER, CAMERA-LANGUAGE SPECIALIST, MARTIAL-ARTS CHOREOGRAPHER, OBSTACLE-DESIGN SPECIALIST, VISUAL STORYTELLER and COMPETITOR-DNA DECODER for a fictional viral short-form universe based on extraordinary Wushu precision-training challenges. Your job is to create highly believable, ultra-photorealistic vertical short videos in which a highly skilled Wushu...
This prompt is written for Seedance 2.5. If you use another model, keep the same obstacle logic and realism goals, but simplify any long instruction blocks into a shorter shot description plus continuity rules, because other models often ignore detailed role-setting.
It assumes a 30-second clip, 9:16 vertical, at 24 fps, ideally as one continuous eyewitness-style take. The first second needs to show the athlete, the opening section of the apparatus, and enough of the route to instantly explain the challenge.
It is tuned for photoreal smartphone footage in traditional Chinese training locations. The common failure points are the model turning it into glossy movie action, adding fantasy architecture, changing the athlete’s face or outfit mid-clip, or breaking the route continuity.
The lines you will most likely edit are the athlete description and the obstacle-location setup. Swap in your preferred performer, uniform color, and exact challenge structure while keeping one clear start, one destination, and a clean final landing.
It assumes a 30-second clip, 9:16 vertical, at 24 fps, ideally as one continuous eyewitness-style take. The first second needs to show the athlete, the opening section of the apparatus, and enough of the route to instantly explain the challenge.
It is tuned for photoreal smartphone footage in traditional Chinese training locations. The common failure points are the model turning it into glossy movie action, adding fantasy architecture, changing the athlete’s face or outfit mid-clip, or breaking the route continuity.
The lines you will most likely edit are the athlete description and the obstacle-location setup. Swap in your preferred performer, uniform color, and exact challenge structure while keeping one clear start, one destination, and a clean final landing.
Questions about this prompt
Which models does this prompt work with?
It is written for Seedance 2.5. The scene direction is model-neutral; only the aspect-ratio line changes between them.
Can I use the output commercially?
Yes. Everything you generate from this prompt is yours to use personally and commercially.
What do I get when I unlock it?
The complete 2,951-word master prompt, copyable in one tap. A single purchase is permanent and stays in your library whatever your subscription does.
