1328 hand-tested AI prompts across image, video, and music — each with full context, variables, and a sample output. Content is authored in Traditional Chinese; the UI here is English.
Veo 3.1 has the deepest grasp of cinematic camera terminology — dolly zoom, rack focus, anamorphic looks, and more all execute correctly. Ideal for sci-fi openings, cinematic-style ads, and trailer intros.
It first declares "locked, static camera," then uses a full sentence, "The camera never moves; every bit of motion is..." to pin down…
The sentence explicitly states "The audio leads the shot," which tells the model to build the visual rhythm around the sound…
A three-act spread-to-explosion-to-reverse-reb…
One prompt cut into four shots, each with its …
Spelling out caustic patterns, dappled light r…
Splitting the JSON into fields locks in a fixe…
Adding the emotional hook of a person dropping…
Scaling unboxing up into a mechanical containe…
Emphasizing natural pores and a dewy glistenin…
A capsule enclosure, city landmarks, and tiny …
Gloved hands on the grips, a slight camera sha…
Intercut close-ups of footfalls with a sweat-b…
Holding the camera at arm's length clearly def…
Put the style keyword first (Veo weights the f…
Spell out translucency, paper texture showing …
Fine crosshatching lines and Art Nouveau gold-…
A strict five-color limit, generous negative s…
A bird's-eye story map packed with discoverabl…
Clearly specify an in-car view with the camera…
A hard steering input, the car body swinging o…
Ultra-fine grain settings: a 45-degree angle, …
A complete JSON storyboard breaks the liquid p…
A fill-in-the-blank all-purpose overhead templ…