How to make a team line-up video with the right name on every face
Number the photos and name them in order, then give Vizard Agent the video whose style you want. It builds one card per person in that layout, keeping each name with its own face, and the same card design can be reused months later when somebody new joins.
What do you type into Vizard Agent?
Write the list plainly, one line per person. The pairing is the fragile part of this job, and a numbered list is far more robust than a description, especially when the names are nicknames that no amount of face-reading would guess. A reference video settles the layout, transitions and music in one go.
Prompt
What does Vizard Agent actually do?
The work is not the animation. It is keeping eleven photos and eleven names paired through every step, and reading the old video's style instead of approximating it: the crop shape, where the name sits, how long each card holds, whether the music lands on the change. In the session behind this article it:
- Looked at each of the eleven photos in turn, then measured the reference video, pulling frames and key timestamps to read its layout, audio and transition points.
- Found a clean background frame to match the reference's own backdrop and designed thirteen cards in that style: the members plus the opening and closing.
- Fixed the hexagonal frame treatment, exported every slide and reviewed them all together before assembling anything, when a wrong name is still cheap to fix.
- Built the video with the reference's transitions and music, checked the render on a contact sheet and a waveform, and reviewed the upload for transitions and audio sync.
- Swapped in a new photo at position five and rebuilt only what changed. A twelfth member was added to the line-up afterwards.
When does this not work well?
Some photo sets cannot be made to match. Wildly different crops, lighting and resolutions between eleven phone photos will show in a grid of identical frames, and Vizard Agent will suggest a consistent treatment rather than pretending the set is uniform. It can't identify faces for you, and past a couple of dozen people the format stops working.
Common questions
Can it read the names off the photos? No, and it should not guess. Give Vizard Agent the list.
Can it match our old team video exactly? That is what the reference is for. Vizard Agent measures it rather than eyeballing it.
Will the name spelling be exactly mine? Yes. Vizard Agent uses your list verbatim, diacritics included.