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.
Leave 'condensing the information' to the model, but lock down 'which words absolutely must appear' with quotation marks — educational diagrams are most vulnerable to labels going off-script, and this...
Naming `orthographic` along with the three drafting views — plan, elevation, and section — makes the model...
The phrase `deconstructed to show the texture of…` ties an exploded-view diagram together with appetite appeal...
The sketch serves as the layout template, and the model only handles the materials — `Keep the exact layout of…` is...
Clear division of labor — placeholder boxes get 'their content swapped in,' while button positions and the grid are 'not to be touched'; UI mockups are most vulnerable to...
The 'make-or-break instant' is written as the shot's explicit task (catching the upper hold perfectl...
Naming the specific technique outright (Fosbury flop) plus the approach-run curve and takeoff foot means the model doesn't have to guess the posture; 'the bar quivering slightly after clearance...
Defining the soundtrack negatively — 'silent except for the edge cutting through snow' — forces a sense of emptiness far better than listing a string of sound effects; waist-deep...
A complete skeleton for multi-shot consistency in Kling 3.0 — appearance is written once in the Master Prompt, individual shots...
Google's own official example of the textbook answer for the five-part 'subject + action + setting + lighting + style' formula; two light sources (cold white...
Instead of adjusting performance with adjectives, write 'where she is and how she feels after laughing' — swap the context around the same verb and the model works out the volume, duration, and...
Native-audio models love to auto-add canned laughter — you have to exclude it negatively with (no studio audience) and then...
The key to a convincing selfie feel isn't the word 'selfie' itself, but writing 'the arm must be clearly visible in frame' as a hard composition requirement; the closing...
First/last frame only gives you the two endpoints — this line carries the entire middle: it locks down the three keys of a match cut: wha...
Before/after shots most easily turn into a hard swap in the last second — `across the clip` requires the...
A time-lapse needs evidence — besides the color temperature shifting from cool morning to warm dusk, two independent time markers are added (clouds drifting slowly, shadows lengthening), so it doesn't...
A runway clip's texture comes entirely from lighting — the phrase `harsh flash photography simulatio...
POV action shots run the biggest risk of subject and threat fighting for focus in the same frame — first-person view naturally turns 'being chased' into an off-screen sense of pressure, using only...
Grok Imagine's native sound effects only land accurately when 'triggered' — the formula is to name the sound (board c...
Even a static portrait can carry drama — exhaling is the only action, and the cold air turns that breath into visible proof; `locked cam...
A vertigo shot is by definition 'dollying in while zooming out' — this line locks down two opposite motions plus a focal-length range (35mm→70mm...
Train subjects are most vulnerable to the camera failing to keep up — `moving alongside` directly specifies a parallel tracking shot at the train's own speed, …
A straight-down overhead shot abstracts the landscape into a flat pattern — explicitly writing `abstract pattern` plus `per…
The soul of a dance piece is 'making the light beam visible' — `a single spotlight above` plus `dust drifting in the light beam` …