About the Oouuh Kitchen Duet AI Video Generator
Oouuh Kitchen Duet AI Video Generator recreates a two-person kitchen performance: on the left, one person strums a ukulele; on the right, the other sings along and dances, filmed on a phone in a home kitchen.
You upload two photos. Photo 1 always becomes the ukulele player on the left and photo 2 always becomes the singer and dancer on the right. Each person keeps their own face, skin tone, gender presentation, hair, facial hair, build and outfit, so a woman and a man, two friends or any pair works. The ukulele, the moves, the kitchen, the camera and the audio come from the reference.
The result runs about 14 seconds in vertical 9:16, at 480p or 720p.
How to make an Oouuh kitchen duet AI video
- Upload person 1. The ukulele player on the left. One person, face clear and well lit. JPG, PNG or WEBP, up to 10 MB.
- Upload person 2. The singer and dancer on the right. Use a different photo of a different person.
- Choose 480p or 720p. 480p is the default and costs less; 720p is sharper. The length and frame follow the reference: about 14 seconds, vertical 9:16.
- Generate and download. Each photo is described first so each person keeps their own look, then both are placed into the duet. Download the MP4 from your Library.
Who plays whom
- Photo 1 → left: the ukulele player, strumming the same ukulele as in the reference.
- Photo 2 → right: the singer and dancer, with the same lip movements, gestures and moves.
- The mapping never flips: photo 1 is always on the left, photo 2 always on the right.
What comes from your photos
- Each person's face, skin tone, gender presentation, hairstyle, hair color, facial hair, build and outfit.
- No beard, glasses or hairstyle is added that a photo doesn't show, and the original performers' hair and chain are not carried over.
Photo tips
- One person per photo, face sharp and evenly lit, upper body or full body.
- Two different people in two different photos; the same file twice is rejected.
- Avoid sunglasses, hats you don't want in the video and heavy filters.
Hands on the ukulele
Fingers on the strings and fast dance gestures are the hardest parts for the AI. Hands can look off and faces can drift for a moment. Check the result before you share it.
About the preview on this page
The video and poster on this page are the reference clip the template follows. They are not a personalized or generated result.
Oouuh kitchen duet AI video credit cost
| Resolution | Cost |
|---|---|
| 480p | 4,063 credits |
| 720p | 8,692 credits |
The reference runs 14.001 seconds (the audio track runs a millisecond past 14s), so it is billed as 15 input seconds, plus a small charge for describing each photo. The cost depends only on the resolution and is shown before you generate.
Frequently asked questions
How many photos do I need?
Two, both required: one for the ukulele player and one for the singer and dancer.
Which photo goes where?
Photo 1 replaces the ukulele player on the left; photo 2 replaces the singer and dancer on the right. The mapping is fixed for the whole clip.
Can it be a woman and a man?
Yes. Each person keeps their own gender presentation, face, hair, facial hair and outfit. A woman stays a woman and a man stays a man.
How long is the video?
About 14 seconds, vertical 9:16, following the reference. The result can end a fraction of a second earlier.
Is the music kept?
Yes. The result carries the reference clip's own audio track, in sync with the performance. No new sound is generated.
Can the hands or faces look off?
Sometimes. Fingers on the ukulele and quick gestures can look unnatural, and a face can drift for a moment. Clear, well-lit photos help.
How many credits does it cost?
4,063 credits at 480p or 8,692 credits at 720p: 15 billed input seconds plus the two photo descriptions.
Is the preview a personalized result?
No. It is the reference clip, not a result made from anyone's photos.
Discover more templates in the trends gallery or explore AI video effects.
Independent AI template. Trendai.video is not affiliated with or endorsed by the people in the reference clip, its creator or the owners of any music in it.