1254 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.
A cinematic 30-second brand story: three shots, with optional voiceover.
The "subject walking slowly in profile" shot fashion TVCs lean on constantly. Veo 3.1 handles fabric physics, hair dynamics, and gloss reflections more reliably than Sora — drop it in as the hero shot for the first 5 seconds of a 15-second ad.
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.