Teardown — Something Older Than the Sun Passed Through: 11 cuts, film + clips + every prompt

Every AI video tutorial shows you the prompt that worked. This shows you all 11, including the dull ones.

One published space documentary — a short-form episode — opened up. The finished film, all 11 generated clips, the 11 stills they were animated from, and for each of the 11 cuts the exact still prompt and motion prompt that produced it, beside the engine tier it was ordered on.

Watch the published cut before you buy: https://youtu.be/i54YXDPwqQ0

Why this genre is worth taking apart

Space footage is mostly slow drift punctuated by a few violent beats, and getting that split right is most of the budget.

Watch how few cuts need the expensive engine. Scale is the hard part in this genre, not motion: the prompts state what fills the frame rather than naming a shot size, because shot-size words do not survive.

What is in the package

• The finished film, as published
• 11 generated clips — the raw shots before the edit
• 11 source stills — the frames each clip was animated from
• PROMPTS.md — one block per cut: framing, tier, still prompt, motion prompt
• production.json — the same record, machine-readable

The routing, in this episode

Every cut ran tier 1. Tier is assigned before a cut is ordered, and it decides the engine. A static shot on the expensive engine is pure waste; a hard-motion shot on the cheap one costs more, because the re-order costs more than the correct order would have.

What the episode argues

3I/ATLAS, discovered July 1, 2025, is only the third interstellar object ever detected. Its methane-to-water ratio is about 11 times anything measured from comets born in our solar system, and ESO/JWST isotope studies suggest it formed around an ancient, metal-poor star — possibly up to 12 billion years ago, far older than the 4.6-billion-year-old Sun. SETI listened for signals and heard only silence. As of mid-2026 it is beyond Jupiter, on a hyperbolic trajectory out of the solar system, never to return.

Three things you can read straight off the prompts

• Identity is locked with a positive count, never a negation — a forbidden thing tends to get summoned.
• Framing is stated as what fills the frame, not as a shot-size name. Shot-size vocabulary is interpreted loosely by every engine we have measured.
• Subject, action and environment are separate lines in the motion prompt. Collapsing them into one sentence is where drift starts.

Honest notice

• Clips are re-encoded for download, not delivered at master bitrate. They are reference and working copies.
• You may use these files in your own commercial and personal work, including client work, and modify them freely. You may not resell or redistribute the package itself, in whole or in part, as a product — including uploading the clips to a stock library.
• This is a record of what one episode took, not a guarantee of a result. Generation models change behaviour between versions, sometimes reversing it, so treat the routing as a procedure you can re-measure rather than a fixed ranking.

—

Where this sits

• AI Video Prompt Craft — $29 — this episode is one worked example; the pack is the reusable standard behind it
• The Prompt Atlas — $49 — every prompt from 83 published episodes, not just this one
• 7 Ways AI Video Burns Your Credits — free — the seven measured credit leaks, at no cost
• The whole catalogue — teardowns, references, skill packs and free calculators, with what each one is for