10,15,30SEC Viral Animal Stunt Video Viral AI Video Prompt
A rider and a huge animal race past a ramp, both flipping through the air before the rider lands back on its back. Dust bursts as they keep charging forward with a wild, high-energy feel.
Master prompt · 3,203 words
# MASTER PROMPT — VIRAL ANIMAL STUNT VIDEO DIRECTOR Copy everything below this line and paste it into ChatGPT as the first message (or save it as a Custom GPT / Project instruction). --- ## 1. ROLE You are the **Viral Animal Stunt Director**. You write production-ready text-to-video prompts (for Seedance, Kling, Veo, Sora, Hailuo, Runway and similar models) for one specific viral stunt format: a person riding a large animal, both launching off a ramp, both flipping through the air separately, and the person landing back on the SAME animal, which keeps running. You do not make random animal videos. You recreate one recognizable stunt formula every time, changing only the character, animal, environment, ramp, trick, camera details and duration. **Language rule:** Talk to th...
This prompt is model-neutral. It was written to generate prompts for Seedance, Kling, Veo, Sora, Hailuo, Runway and similar tools, so you can paste the output into whichever one you use. If your model prefers shorter prompts, keep the stunt beats, same-animal remount, and strict side-profile camera, then trim extra wording around texture and motion.
It assumes a single short clip in 10, 15, or 30 seconds, starting with the rider already mounted in frame one. The framing is locked to a true side view the whole time, with the full animal profile visible and the movement traveling horizontally across frame.
It is tuned for glossy viral stunt realism with readable body mechanics. Models often get this wrong by switching to a front or 3/4 angle, throwing the rider off instead of an active jump, using a different animal on landing, or skipping the visible ramp climb.
The lines you will actually customize are the subject choices: the character reference, the animal, the environment, and the duration. If needed, also change the stunt trick and the ramp type so they fit your animal and location.
It assumes a single short clip in 10, 15, or 30 seconds, starting with the rider already mounted in frame one. The framing is locked to a true side view the whole time, with the full animal profile visible and the movement traveling horizontally across frame.
It is tuned for glossy viral stunt realism with readable body mechanics. Models often get this wrong by switching to a front or 3/4 angle, throwing the rider off instead of an active jump, using a different animal on landing, or skipping the visible ramp climb.
The lines you will actually customize are the subject choices: the character reference, the animal, the environment, and the duration. If needed, also change the stunt trick and the ramp type so they fit your animal and location.
Questions about this prompt
Which models does this prompt work with?
It is written for Seedance, Kling, Veo, Sora and Hailuo. 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 3,203-word master prompt, copyable in one tap. A single purchase is permanent and stays in your library whatever your subscription does.
