The whole process
How to make a tiny desk AI video
Four steps, one payment, about five minutes of your time. There is no prompt to write, no model to subscribe to, and nothing to install: the concert footage already exists, and the only thing you bring is the faces.
The part that decides whether the video is good is the photos. Most of this page is about getting those right the first time, because a bad photo is the only reason a render comes back looking like someone else.
Take the photos
One portrait for Solo, five for Five. Face on, daylight, eyes to the camera, nobody else in the frame. A phone photo is fine as long as the face is sharp and at least 800 pixels across.
Pick a mode and the order
Solo puts one face in the singer's spot. Five fills the whole band, and the order you upload in is the order people stand: 01 singer, 02 keyboard, 03 back left, 04 back right, 05 saxophone.
Pay once
One video is $4.99, three are $9.99, five are $14.99. No subscription and nothing renews. If the render comes back wrong, reply to the receipt within seven days and the order is refunded.
Download and post
The video lands on the order page in a few minutes: fifteen seconds, 720p, vertical, sound already in the file. Download it the same day, because the file is cleared after seven days.
What the photos need
Works
- Face filling a third of the frame or more
- Daylight, or a room light that is not behind the head
- Eyes to the camera, neutral or half smiling
- Nobody else in the shot
- Sharp focus, no motion blur, and not a screenshot of a photo
Comes back wrong
- Group photos where the face is a small part of the frame
- Sunglasses, a mask, or the face turned away
- Heavy filters or beauty modes that resample the face
- Night shots with noise on the skin
- A photo of a screen, or a print of a print
Where the five faces land
In Five mode the upload order is the standing order. Get it wrong and the video comes back with the wrong person in front, which is the mistake people make most often.
- 01
Lead singer
Centre of frame, closest to the camera, mouth open on the first word of the chorus. This is the face people look at, so it is the one your group will recognise first.
- 02
Front keyboard
Left of the singer, turned three quarters away, hands on the keys. They are in focus for most of the clip because the camera starts here.
- 03
Back left
Behind the keyboard, half hidden by the singer when the camera swings. They still show up in the wide shot and in the last beat.
- 04
Back right
Opposite the back left, on the side the saxophone leans into. They get one close pass in the middle of the clip.
- 05
Saxophone
Right of frame, the only person whose hands are visible the whole time. The horn is part of the shot, so their face sits behind it.
What you get, and what it costs
A vertical MP4, 15 seconds, 720p, 9:16, with the sound already in the file. No watermark and no captions. $4.99 for one, $9.99 for three, $14.99 for five. One model, 720p, no subscription, and a seven-day refund on every order.
Renders take a few minutes at normal load. You can close the tab, the order page keeps working without you, and the video is downloadable from it for seven days.