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.
全片單鏡不剪，卻用「ramping into deep slow motion → snap…
三段式——第一段全是「攝影機規格」（the camera IS her eyes、完全不穩、…
第一行就用否定句 don't use one camera angle or single …
Generate a professional turntable-quality 360° product video from text alone: constant angular rotation speed, a seamless loop with matching start and end frames, and continuous, non-flickering highlights on reflective materials — ready to use as the main video on a Shopee or momo listing page or as a livestream standby screen.
A macro headlight shot rising on a crane into …
Pure black with a single top light and diamond…
Still-life elegance hard-cutting to a spray cr…
Breaking out head, eye, and ear movements whil…
Vertical, no music, and fingernail tapping sou…
Anchor the wuxia style to Crouching Tiger, Hid…
Break the dragon transformation into a gradual…
Use timecoded three-part blocking (windup, lun…
Lock four parameters per shot: focal length (2…
Build negative space and brushstroke texture b…
String three shots together: blue-and-white po…
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…
Handheld camerawork, reflections on wet paveme…
Swirling patterns as liquid meets milk, ice cu…
A night scene, colored lights, and dynamic mov…
A timelapse style with lightning bolts strikin…
Focusing on slow bites and the gooey, gurgling…
It quantifies everything: composition (glacier…