Face clearly visible
Eyes and mouth sharp and toward the camera. Blurred or profile shots come back less like your child.
Upload one photo of your own baby or toddler and they take over the argument: pointing at the lens, one small "stop" hand, a shrug, a giggle behind their hands — lip-synced to Imael Angel's "BAD TIMES". 4 credits, no prompt, no watermark.
One photo of your child; the moves, camera and song are already in the template.
The render keeps your child's face, hair and clothes, so photo quality decides the result.
Eyes and mouth sharp and toward the camera. Blurred or profile shots come back less like your child.
At least head and shoulders, so clothes and proportions carry over.
Daylight or a bright room, no heavy filters.
One child per photo, nobody else in frame, nobody holding them.
Your toddler performing the argument lip-sync in your own room: pointing, a stop hand, a shrug, a giggle.
Only your own child, and only if you are the parent or legal guardian.
A toddler who can stand and hold their head steady reads best.
Yes. It is never published or shown to anyone else.
Usually another person in frame, a heavy filter, or a face that is not clear. Credits return automatically.
15 seconds, 9:16, with the song and no watermark.
4 credits on Budget, 8 on Balanced, 15 on Premium.
What is BadTimes AI?
Send this question straight to your assistant — the prompt already carries this site address.
Opens in a new tab