Photo to video

Rap Duo AI: you and a friend, rapping in the hotel lobby

The rap duo trend everyone is remaking — two people trading bars in a marble hotel lobby, the "Migos AI" video — with your two faces in it. Pick who stands left and who stands right, upload a photo of each, and the performance plays out with you two in it: the moves, the hand gestures, the lip movement in time with the beat. The performance, the beat and the lyrics are our own, made for this; nothing is taken from anyone's video.

What you get

  • Your rap duo video (720p, with sound)

135 credits per run

Vertical 9:16, for TikTok, Reels and Shorts (10 s)
The inputs of the run shown on this page. Change anything before you run.
One person, face clear, looking at the camera
One person, face clear, looking at the camera

Usually ready in about 10 minutes · Free to try — sign in when you generate.

How it works

  1. 1
    Upload a photo of each person and choose who stands left and right
  2. 2
    AI puts the two of you into the performance
  3. 3
    Download the video and post it

A real run

Made with this page and not retouched — what went in comes first.

The performance you step into: our own, with an original beat and lyrics
Left photo (an AI-generated person, not a real one)
Left photo (an AI-generated person, not a real one)
Right photo (an AI-generated person, not a real one)
Right photo (an AI-generated person, not a real one)
The rap duo video (landscape, 10 s)
Another pair: left (AI-generated, not a real person)
Another pair: left (AI-generated, not a real person)
Another pair: right (AI-generated, not a real person)
Another pair: right (AI-generated, not a real person)
Vertical 9:16, for TikTok, Reels and Shorts (10 s)

FAQ

Is this the Migos video?

No. It is the trend — a two-person rap in a hotel lobby — done with a performance, beat and lyrics we made ourselves. Wisaven is an independent tool and is not affiliated with Migos or with any original performance.

Whose photos can I use?

Your own, and a friend who has said yes. Do not use anyone's photo without their permission. The video stays in your library and cannot be published to the gallery, because it shows real people's faces.

Whose voices are rapping?

The two voices of the original track, not yours: your faces take over the performance, the soundtrack stays as it is, and the lips move with it.

What photos work best?

One person per photo, face front-on and well lit, not covered by sunglasses, hands or hair; at least 300 pixels on each side. Photos are converted to JPG before upload.

How long does it take, and what do I get?

About 6–10 minutes for 10 seconds, 10–20 for 15; you can leave the page, the video is saved to your library. You get a 720p MP4 with sound, landscape 16:9 or vertical 9:16, without a watermark. 10 seconds is 135 credits, 15 seconds 200.

Can I use the results commercially?

Yes, on every plan, the free one included — what you make is yours, subject to the Terms and to the rights in what you upload.

Is it free to try?

Yes — new accounts get free credits. Generating signs you in; paid plans add more monthly credits.

Need just one step?

More use cases

All use cases →