USA Gymnastics Performance Viral AI Video Prompt
A tense arena routine by an adult gymnast on the balance beam, with a stumble on landing, in a packed championship venue. The crowd feels electric and suspenseful.
Master prompt · 4,428 words
You are PODIUM ENGINE, a dedicated production system for 30-second photoreal vertical gymnastics films set at a major international competition and generated in a single Seedance 2.5 pass with no editing, no stitching, no multi-clip assembly and no post-production, which means every prompt you write must be complete, self-contained and ready to paste straight into Seedance without a human rewriting it afterwards. You operate in four strictly gated stages that you never skip, never merge, never reorder and never run ahead of: you deliver exactly one stage, then stop and wait for my next instruction, and if my instruction is ambiguous you default to the earliest stage that has not yet run rather than guessing forward. You never explain your reasoning, never narrate what you are about to do,...
This prompt is written specifically for Seedance 2.5. It is not a simple one-shot scene prompt but a staged system that first generates topic ideas, then builds a very long final production prompt. If you use another model, you will need to strip out the Seedance-specific staging and likely shorten the final output heavily.
It assumes one continuous 30-second vertical clip at 1080x1920, 30 fps, with a locked broadcast camera and no cuts or reframing. The frame is designed as a full-body, head-to-toe sports coverage view from a fixed tripod position, not a moving social camera.
The look is photoreal televised championship realism. It is tuned to an isolated live broadcast feed, with arena lighting, natural motion blur, soft crowd falloff, and no stylized grading. The model will most often get body age, facial consistency, apparatus terminology, and camera obedience wrong unless those sections stay very exact.
The lines you will realistically edit are the chosen athlete from the casting bank and the venue selection, plus the topic number or exact routine moment you want the final episode built around.
It assumes one continuous 30-second vertical clip at 1080x1920, 30 fps, with a locked broadcast camera and no cuts or reframing. The frame is designed as a full-body, head-to-toe sports coverage view from a fixed tripod position, not a moving social camera.
The look is photoreal televised championship realism. It is tuned to an isolated live broadcast feed, with arena lighting, natural motion blur, soft crowd falloff, and no stylized grading. The model will most often get body age, facial consistency, apparatus terminology, and camera obedience wrong unless those sections stay very exact.
The lines you will realistically edit are the chosen athlete from the casting bank and the venue selection, plus the topic number or exact routine moment you want the final episode built around.
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 4,428-word master prompt, copyable in one tap. A single purchase is permanent and stays in your library whatever your subscription does.
