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.
B-roll footage to intercut into documentaries, long-form YouTube videos, and brand story films — not the main shot, but atmospheric filler that supports the narrative. Sora 2 is particularly good at capturing mood in shots with no people in them.
The interviewee close-up for brand documentaries, internal-training onboarding, and testimonial walls. Veo 3.1's natural eye contact and lip-sync accuracy are good enough to carry the lead with no cut-and-paste.