Feedback
AI Ad Video Example
Loading...
Migos AI Video Generator
Turn two cleared portraits into a vertical 9:16 rap duet — the Migos AI Video Generator swaps the lead while a single mic stays put.
All Tools
Discover our comprehensive AI-powered animation toolkit
MiniMax H3
MiniMax H3 AI Video Generator
Seedance 2.5
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
FLUX 3 Video Generator
Kling 3.0
Next-Gen AI Video Generator
Grok Video Generator
Create Videos from Text or Images with AI
MiniMax H3 video generator
MiniMax H3 AI Video Generator
Seedance 2.0
The Future of AI Video Is Here.
A Two-Person Format You Can Cast Yourself
A purpose-built video tool that turns two cleared reference portraits into a side-by-side booth performance, so you can ride the trend with faces you actually have the rights to use.
- Cast Two Subjects Into a Single FrameSet up a 9:16 frame from two independent cleared portraits — one subject anchored left, the other right — inside a seamless amber-orange studio where a black microphone drops down between them.
- Distinct Identities With a Trading LeadEach face must remain legible and locked to its own half of the frame. One voice opens the verse with easy gestures while the partner listens, and the two switch who is leading partway through.
- Inspiration That Respects Usage RightsTrends are inspiration, not permission. Build your duo from fictional adults, consenting friends, or even pets, and pair them with audio you recorded or licensed rather than a famous voice or a chart track.
Three Steps to a Two-Person Booth Clip
From a pair of reference portraits to a finished side-by-side performance in a terracotta studio — here is the whole path.
What Keeps a Two-Person Clip From Falling Apart
Identity, timing, staging, and clearance are all steered through the prompt — the reason a side-by-side booth clip holds up from opening frame to final beat.
Keeping Both Identities Separate
Label one subject LEFT and the other RIGHT, leave breathing room near the mic so limbs and bodies never blend, and dial motion down before layering style if the two faces begin to bleed together.
A Lead That Changes Hands
Describe the handoff in words: the first performer delivers while the second reacts, then midway they switch without swapping positions — small nods and light hand gestures read better than nonstop movement.
A Locked Terracotta Set
Hold the shot to a seamless matte-orange wall and floor, front-lit softly, with one black microphone positioned dead center, a wide lens that never moves, and both sets of feet visible in frame.
Casting You Can Legally Use
Draw your performers from invented characters, consenting friends, animals, or any other original pairing, give them a soundtrack you own, and never present a synthesized famous face as real footage.
Directing Both Performers by Prompt
You decide who starts, how the other answers, and whether the mood stays mellow or builds — plenty of latitude to push the template toward a friendship gag, a pet bit, or your own creator concept.
Fixing One Flaw at a Time
Rewrite only the sentence responsible for a single problem — fused faces, overlapping hands, a wandering lens — so each new attempt is easy to compare against the last instead of a full restart.
Two-Person Booth Clip FAQ
Answers to the questions people ask most about the paired-booth format, reference portraits, usage rights, and the rendering model underneath.
Which visual elements make the orange-booth duo look?
Three signals do most of the work: a burnt-orange backdrop, one microphone suspended between the two figures, and a call-and-response rhythm. The look traces back to Quavo and Takeoff performing “Hotel Lobby” on A COLORS SHOW.
Is it necessary to supply two different photos?
Yes, and strongly so. The effect only lands if the model can distinguish two people and pin each one to their own half, so use cleared images with similar lighting and clearly visible faces.
May I upload a famous person's photo or the track from the original video?
Only work with assets you have the right to use — images, likenesses, video, music, and vocals included — and never let a synthesized famous face pass as real. Original subjects plus audio you own keep you on safe ground.
What causes the two faces to merge?
It usually traces back to the inputs: dark, cluttered, or unlabeled portraits leave the model without an anchor. Use one person per image, spell out LEFT and RIGHT in your prompt, and reduce overlapping hand movements.
Which Dreamina model fits this workflow best?
This page defaults to Seedance 2.5 because it accepts multiple reference images and lengthy, granular direction. Availability and credit cost vary with your account tier and region.
How can I prevent position swaps or mirrored movement?
Pin each performer to one side for the entire clip, lay out the order of turns step by step in your prompt, and keep reactions subtle and personal so the two never echo each other.
Make a Two-Person Booth Clip With Your Own Cast
Choose two people or pets you have permission to feature, spell out how each one stands and responds, and let Seedance 2.5 deliver the finished side-by-side video.