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.
Runway's official examples always use four sentences — the first covers only the camera position, the second only the setting, the third only the action, the fourth only…
The camera is locked and all the action is handed to the arriving train — an empty platform first sets a clean static baseline, then the doors open to reveal a packed car, landing the before/after contrast…
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 …
Gen-4's camera control feature. The subject stays fixed while the camera orbits 180 to 360 degrees.
Upload 2 still illustrations or posters, and Gen-4 fills in the motion transition between them.