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.
Native audio is the thing models most often bury under auto-generated music — start by setting the spec with `Native audio. 48kHz.`...
Gen-4 is image-to-video first — the starting image already locks in the look, composition, and color grading, so the prompt is almost entirely 'describe the motion only'…
E-commerce product rotations are most vulnerable to uneven speed and lighting jumps — this prompt explicitly states `no acceleration or dec…
The believability of a destruction shot rests on debris trajectories and dust — `physics-accurate trajectories` combined with …
Kling 2.5 Turbo can handle 'multiple shots written into one sentence' — low-angle wide shot → dolly back retreat …
The same 'one continuous sentence' disaster template applied to a different subject — a mechanical serpent bursts through the asphalt, a dolly back through the smoke, a cut to …
Sora 2 natively generates dialogue — a `Dialogue: "..."` field produces the voiceover directly; a lived-in, cluttered background …
Specifying three powder colors (crimson/cobalt/gold), backlighting to make the particle edges glow, and a pure black background turn a …
Breaking `Style / Audio / Duration` into explicit slots — a single Audio line lists ambient music, birdsong, breathing, and footsteps …
The `Camera movement:` field includes time-segmented beats (a dolly forward for the first 3 seconds, then a push-in to the hands) …
Narrating through 'emotion and light' rather than piling up camera-language terms — an expression that blends surprise and joy, …
Wan 2.5 generates picture and sound together in one pass — a `Sound of ... narrator says: '...'` field …
A Dutch angle plus a slow zoom out create unease, while a `Sound of rai…` field …
Turns an unboxing into a premium first-person clip usable on both e-commerce product pages and Reels: hands entering frame to unbox, a slow-motion lid-lift moment, and realistic cardboard-box ambient sound — no hand model or studio required to capture that buyer's-first-unboxing anticipation.
Sora 2 responds best to this kind of writing for 'physical realism' — using a dedicated `Physics:` section to call out surface tension, …
The key to image-to-video is 'only describe the change, don't redescribe what's already in the frame' — this prompt uses five sections, `Transformation/Li…
Write the audio as a bulleted `Audio requirements:` spec — the bag-impact sound 'synced to the motion,' breathing, …
The hardest part of a two-person dialogue is 'keeping both characters stable' — this prompt uses `[Character Cameo: …]` to separately lock in the persona of the host and the guest, …
Mood pieces most easily turn into a pile of adjectives — this one instead uses five fields, `Mood / Atmosphere / Detail…
One prompt runs through four shots: a low-angle wide shot establishing the giant figure, a dolly-back retreat, a cut to handheld footage following the fleeing crowd, …
The tension in sci-fi action comes from 'the camera suffering along with the characters' — handheld FPV riding on the shoulder, a whip-pan catching a terrified face, …
A clean studio shot with mid-air assembly and …
Macro framing plus butter bubbling and rising …
Rim lighting gives the frame a 3D feel, and a …