One of you sits on the table. The other walks in and ends it. Two photos, one scene, maximum deadpan.
The skit needs exactly two characters, and Duo mode maps them to your two photos:
Nobody from the original video remains — both characters are regenerated from your photos, in the same concrete cafe with the same beat-for-beat timing and the white POV caption.
Solo portraits work far better than group shots — the AI needs a clear, unobstructed view of each face.
Two photos shot in similar lighting blend more naturally into the same scene.
Run the free 5-second preview with both photos before paying — it shows the first sit-down with your two faces in role.
You upload two photos. Photo 1 becomes the person sitting on the tiny table; photo 2 becomes the regular in the grey suit who walks in, sits on the ledge and puts her cup on the table. The AI keeps each face locked to its role — no mixing.
Whoever's first time it is — that's the joke. The person on the table does the confident sit, the slow glances and the embarrassed climb-down; the regular only walks in and delivers the cup. Pick the friend with the better deadpan for the table.
Two clear, front-facing photos in even light, one per person, at least 300 × 300 px. JPG or PNG, up to 6 MB each. Confirm you have permission to use both photos — everyone pictured must be 18 or older and have agreed.
Yes — the 3-Pack is $19.90 for three separate 15-second videos and the credits stay in one browser wallet, so one person can pay and the pack can cover duo videos for the whole group chat.
One photo. Free 5s preview. Full 15 seconds from $9.90.
Make my fancy cafe video