Input portrait → generated video
A fictional adult portrait was used for the lead vocalist with the Tiny Desk AI (Desk Concert) template configuration.
Requested 5 seconds · 480P · 9:16
One photo. Lead vocalist at the desk.
Generated demo using an AI-created portrait of a fictional adult.
Trend template guide
Make a Tiny Desk-style AI performance with one portrait. Choose duration, quality and framing, then review your credit quote. This independent template is not affiliated with NPR or Tiny Desk.
Step-by-step guide
Bring one clear portrait. The desk-concert scene, band and camera work come with the template.
Upload one clear, unobstructed portrait to replace the vocalist behind the desk. There are no separate photo slots for band members.
Start with 5 seconds, 480P and a vertical frame, or choose 1–15 whole seconds, 768P or a wide frame. Shorter clips cover fewer shots of the performance.
Sign in, check the credit quote and generate. The model creates audio using the template reference; view and download the finished video in My videos.
About the template
Your portrait is assigned to the lead vocalist behind the desk, including the laughing close-up when it appears. The other performers have no photo slots. The template guides the scene, camera and generated audio; results may vary.
Make it your own
These are the reference clips, not guaranteed shots in the generated result. Choose any whole-second duration from 1 to 15 seconds, 480P or 768P, and 9:16 or 16:9.
| Duration | Reference footage | Example credits |
|---|---|---|
| 5 seconds | Opening vocalist, then the band. | 35 |
| 10 seconds | The opening and band, followed by a laughing close-up of the vocalist. | 45 |
| 15 seconds | The earlier shots and the saxophone solo. | 50 |
Examples use one photo, 480P and 9:16. Prices may change; the exact quote for your choices appears before submission. The finished video may run up to about 0.7 seconds longer.
One clear, front-facing portrait is required for the lead vocalist. There are no separate photo slots for the band or saxophone player. Use your own photo or one the person has explicitly permitted you to use; generated identities may vary.
The model generates audio guided by the template’s reference; the app does not simply add the original recording to the output. Lyrics, melody, timing and vocal character can vary. You cannot upload a song or audio track, choose a different song, or provide custom lyrics.
If a generation job fails, the credits charged for that job are returned automatically. This failed-job credit return is separate from a refund request for a paid order.
