Hotel Lobby AI video: the rap duo trend, explained
Two people, one hanging mic, a bright orange booth. Here's how to make your own version from two photos, with ten prompts that nail the look.
Video2 people9:16
The trend
What is the Hotel Lobby AI trend?
Despite the name, there is no hotel lobby in these videos. The trend recreates the look of Quavo and Takeoff's 2022 performance of “HOTEL LOBBY (Unc & Phew)” on A COLORS SHOW: two performers side by side in front of a flat, bright orange wall, sharing one microphone that hangs from the ceiling, trading bars with big hip-hop hand gestures.
In September 2026 AI versions exploded on TikTok, X and Reels: best friends, couples, siblings, grandparents, cats and cartoon characters all took the mic. Most versions are made from two photos, either by face-swapping onto a template or by generating a brand-new performance in the same orange-booth style. That second approach is what the prompts below are for.
The format is also controversial: Takeoff died a few months after the original performance, and some people find putting other faces on it uncomfortable. The respectful route is to create your own original performance in the same style, with people who agreed to be in it.
Keep it respectful. Use your own photos or friends who said yes. Don't put real public figures in it without permission, and don't upload the original song as your own: use the platform's licensed sound or your own AI-made beat.
How to
How to make a Hotel Lobby AI video for free
Get two clear photos
One photo per person (or pet), face and upper body visible, good light. Similar framing in both makes the duo look natural.
Make the booth still (optional)
In Jimeng, Doubao or Gemini, upload both photos and use prompt #1 to create a single still of the two of you in the orange booth. This keeps faces consistent.
Animate in an image-to-video tool
Upload the still (or both photos as references) to Kling, Jimeng or Hailuo and paste a prompt below. Keep the camera mostly static, like the original.
Generate 8–10 seconds, 9:16
Short clips keep the lip-sync and hands clean. Make two or three takes and keep the best.
Add the sound
Add the trending sound inside TikTok, Douyin or CapCut, or make your own beat in an AI music app, and line up the mouth movements.
Guide
Tips for a convincing Hotel Lobby AI video
Get the look right first
The trend is recognisable from three things: a flat, saturated orange background, one microphone hanging from above between the two performers, and a static, front-on camera. If your result does not read as 'the orange booth video', check those three before anything else. Extra props, moving cameras or a different colour quickly make it look like a generic music video.
Make a still before you animate
Image-to-video models keep faces more stable when they start from a good still image. Creating the two-person booth still first (prompt #1) lets you fix faces, outfits and framing before you spend credits on video. Once you like the still, upload it as the first frame and describe only the motion.
Lip-sync and gestures
Rap videos depend on mouth movement and hands. Ask for 'clear lip movement in time with the beat' and 'big hip-hop hand gestures' rather than complex body motion. Keep clips to 8–10 seconds; longer clips tend to lose sync. If your tool supports audio-driven lip-sync, upload your own beat or voice line so the mouths match a real sound.
Audio and rights
Do not upload the original song as your own track. Use the licensed sound inside TikTok, Douyin or Reels, or make an original beat with an AI music tool. This keeps your video from being muted or removed and respects the artists behind the original.
Respect the people in it
Only use your own face and friends who said yes, and avoid using real public figures. A playful original performance in the same visual style is both the most fun and the most respectful way to join the trend.
Prompts
10 copy-ready Hotel Lobby AI prompts
All prompts keep the trend's signature look: orange booth, one hanging mic, two performers. Upload your two photos first.
10 of 10 shown
#01
The booth still (start here)
Photorealistic still of the two people from the reference photos standing side by side in a minimalist music studio booth with a flat, bright saturated orange wall and floor, a single vintage studio microphone hanging from the ceiling on its cable between them at mouth height. Both wear casual streetwear, mid-gesture as if rapping, confident expressions. Even soft frontal light, knee-up framing, centered symmetrical composition, faces identical to the references, 9:16.
The two people stand in a flat bright-orange studio booth sharing one microphone hanging from the ceiling between them. They take turns rapping into it with big, confident hip-hop hand gestures, pointing at the camera, nodding to the beat, leaning toward the mic on their verses. Static front camera, knee-up framing, even soft light, accurate lip movement, faces consistent with the photos, 9:16, 10 seconds.
An elderly couple from the photos raps together in a flat bright-orange studio booth under a single hanging microphone, delivering bars with surprising swagger: finger points, shoulder bounces, the grandma adjusting her glasses mid-verse, both cracking a smile at the end. Static camera, knee-up framing, soft even light, gentle natural motion, 9:16, 10 seconds.
Two best friends in matching oversized hoodies and bucket hats perform a high-energy rap duet in a flat bright-orange booth with one microphone hanging between them, finishing each other's lines, synchronized hand waves, a quick handshake on the beat drop. Static front shot, knee-up, even light, crisp lip-sync, faces as in the reference photos, 9:16, 8 seconds.
A couple from the photos raps a playful back-and-forth duet in a flat bright-orange studio booth, one hanging microphone between them. One delivers a line, the other reacts with a laugh and a shoulder bump, then they lean into the mic together for the hook. Static camera, knee-up framing, soft light, natural chemistry, accurate mouth shapes, 9:16, 10 seconds.
Two cats from the photos stand upright on their hind legs in a flat bright-orange studio booth with a single microphone hanging between them, bobbing their heads to the beat and gesturing with their paws like rappers, mouths opening in time with the rhythm. Keep each cat's fur colour and markings exactly, static front camera, knee-up framing, soft even light, comedic and cute, 9:16, 8 seconds.
Two anime characters based on the people in the photos perform a rap duet in a flat bright-orange studio booth with one hanging microphone between them, dramatic hand gestures, hair swaying, speed lines on the beat drop. Japanese anime style, clean cel shading, bold outlines, static camera, knee-up framing, 9:16, 8 seconds.
Pixar-style 3D versions of the two people from the photos rap together in a flat bright-orange studio booth under one hanging microphone, big expressive eyes, exaggerated cartoon gestures, one does a little shoulder shimmy while the other points at the camera. Soft studio lighting, subsurface skin, static camera, knee-up framing, 9:16, 8 seconds.
3Dcartoon
中文版 Chinese version
照片中两人的皮克斯风 3D 形象,在纯亮橙色录音棚里、一支悬挂麦克风下一起说唱,大眼睛表情丰富,卡通手势夸张,一个人小幅抖肩,另一个人指向镜头。柔和影棚光,次表面散射皮肤,固定机位,膝盖以上构图,9:16,8 秒。
#09
Office duo after hours
Two coworkers from the photos, still in office shirts and lanyards, rap a confident duet in a flat bright-orange studio booth with a single microphone hanging between them, one loosening their tie, the other holding a coffee cup like a prop, deadpan expressions turning into grins. Static front shot, knee-up, even light, comedic timing, 9:16, 10 seconds.
The two people from the photos wear modern hanfu-streetwear fusion outfits and rap a duet in the same minimalist booth, but the flat wall is a warm vermilion-orange with a faint ink-wash mountain texture, a single microphone hanging between them, folding fan used as a hand prop on the beat. Static camera, knee-up framing, soft even light, crisp lip movement, 9:16, 10 seconds.
The name comes from the song, “HOTEL LOBBY (Unc & Phew)”, performed by Quavo and Takeoff on A COLORS SHOW in 2022. The look is the COLORS studio: flat orange wall and a single hanging mic.
Can I make it free?
Yes. Kling, Jimeng, Doubao and Hailuo offer free daily or starter credits at the time of writing, enough for a couple of short clips. Some template apps charge for the full video.
Can I use my pet or a cartoon character?
Yes. Pets and original characters are some of the most popular versions. Describe them clearly and keep their fur or design consistent, like prompt #6.
Is it OK to use celebrity faces?
We don't recommend it. Using a real person's likeness without permission can break platform rules and personality-rights laws, and it is part of why the trend has drawn criticism.
How do I get the lip-sync right?
Keep clips short (8–10 seconds), keep the camera static, describe the mouth movement in the prompt, and line the clip up with the beat in CapCut. Kling 4.0 can also generate audio with lip sync directly.