Decide the joke before you pick photos
Every good version has one idea: the team that just lost, the league’s last-place manager, the friend who is always late. Decide who the joke is about, then cast around it. That person usually belongs in the laughing close-up or on sax, because those are the two shots people remember.
Write the caption now too. The video does not add text, so the caption is where you name the team, the league or the occasion.
Who goes in which slot
Photo 1 is the lead at the desk microphone and red keyboard, visible in the opening band shot. Photos 2 and 3 are the backing singers standing behind on the left and right. Photo 4 is the close-up that breaks into laughter in the middle shot. Photo 5 is the saxophone player who closes the clip.
You never photograph instruments, the desk or the shelves; they come from the reference scene. All you supply is up to five portraits.
How many photos, and which ones
One to five, one adult per photo; any role you leave empty is played by someone you added. A chest-up selfie facing the camera in daylight works better than a dramatic shot from a party. If your only picture is a team photo, crop each person into their own image first; a single group photo will not give the band separate faces.
Skip sunglasses, masks, heavy filters and steep angles. Those are the first places the likeness slips.
Sound, length and resolution
The clip is 14 seconds, vertical 9:16. 480p costs 10 credits and 720p costs 22. You can keep the sound from the reference clip or export it silent and add the trending “Outstanding” sound inside TikTok or Reels, if it is available for your account.
An optional note starting with “Outfit:” lets you nudge what the band wears, for example matching team colours.
Before you post
Watch the whole clip. Faces can drift and the sax can bend; if something is off, a sharper portrait in that slot usually fixes it. When it looks right, post it with the AI-generated label switched on, and only share versions everyone in them has agreed to.