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.
The hardest part of a two-person dialogue is 'keeping both characters stable' — this prompt uses `[Character Cameo: …]` to separately lock in the persona of the host and the guest, …
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.