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.
Pencil underdrawing lines, cold-press paper te…
Put the style keyword first (Veo weights the f…
Locking in the NES limited palette plus pixela…
Specify the SNES generation, an idle animation…
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…
A first-person helmet-cam view, lean into the …
An in-car mount, flying mud, and handheld shak…
Clearly specify an in-car view with the camera…
A hard steering input, the car body swinging o…
A locked tripod, backlit steam from a pendant …
A side-angle slow-motion capture of the milk p…
Ultra-fine grain settings: a 45-degree angle, …
Nightclub mood lighting, backlit bottles, a sc…
A 15-second single take of dual-layer nano com…
Crushing the core triggers a burst of feathers…
An orbiting camera follows a rippling car shel…
A brass monocle, a steampunk airship, gears tu…
Gear towers, elevated railways, and a drifting…
Handheld camerawork, reflections on wet paveme…
A tight focus on the single action of a vendor…
A complete JSON storyboard breaks the liquid p…