A camera move decides what the viewer looks at and how they feel about it. Here are twelve, each with a clip made in NOLGIA, the exact prompt that got it, and the move it is most often mistaken for.
People move badly in AI video when the prompt names an action, not its physics. One backflip on four models from the same frame, plus three pairs on weight, contact and timing.
Three sentences make a clip read as filmed: a named light source, a walk with weight, a camera someone is holding. Each tested before and after on Kling v3.
How to write for Seedance 2.5 on NOLGIA: text to video, a still as the start frame, a take as @Video1 with its sound, the six aspect ratios, 4 to 30 seconds, and what it refuses.
The seven ways a video prompt goes wrong, each rendered twice on Kling v3: the vague prompt, then the same prompt with one fix. Copy the fixes, and read what a seed does not do.