Put your duo in the orange booth. Upload two separate portraits or one photo of two people, then create a 15-second video with the reference performance’s moves and camera cuts, plus original audio.
Generate VideoJPG or PNG up to 10 MB | 15 seconds | 480p or 720p | Vertical 9:16
The Hotel Lobby AI trend is a viral social meme format that recasts two people into a bright orange studio booth trading rap verses. Inspired by the 2022 performance by Quavo and Takeoff, creators now put friends, partners, kids, or pets into the booth to trade lines under a hanging microphone.
The Hotel Lobby AI trend recasts the two-person orange-booth performance associated with Quavo and Takeoff’s 2022 A COLORS SHOW appearance. Friends, couples and families take the performers’ places under the hanging microphone.
Use the 15-second reference shown in the generator to make your version. Your photos set the performers’ identities; the reference supplies the orange backdrop, microphone, movement, timing and camera cuts. Two separate photos map to the left and right performers. With a shared photo, the person on each side maps to the same side in the video.
Choose 480p or 720p. Your output is a 15-second vertical 9:16 MP4 with the original reference audio, ready to play and download in My Work.
Creating your personalized rap duo video usually takes a few minutes from photo upload to final download.
Choose Two Separate Photos for two portraits, or One Photo (Two People) for a shared photo. The left and right photos set each performer’s position. You can swap the two portraits before generating. Upload JPG or PNG files up to 10 MB each.
Every video is 15 seconds long and uses the full reference performance. Choose 480p for 60 credits or 720p for 80 credits. The cost is shown before you generate.
Sign in and press Generate Video. Your task appears in My Work while it processes. When it finishes, play or download the 15-second vertical MP4 with original audio.
Choosing clear source photos is the most reliable way to get sharp character likenesses and clean movement in your finished video.
Use photos where both subjects look straight ahead into the camera. Angled head tilts and side profiles make it harder to align facial features and mouth movements with the rapping vocals.
Clear, diffused lighting across the face captures eye details, skin tones, and facial structure cleanly. Avoid dark indoor snapshots, harsh backlight, or strong side shadows that hide facial features.
Photos showing the face and upper body give the model clear details for the performer’s appearance.
When using the two-photo workflow, make sure each uploaded image contains only one person. Cropped group pictures with stray hands or background faces can cause the tool to select the wrong subject.
If you upload a single shared photo, choose an image where both individuals stand side by side with clear space between their heads. Overlapping faces or tight embraces make separating the two performers harder.
For dogs and cats, use an upright, front-facing photo with the face, neck and chest visible.
From birthday celebrations to playful social clips, the orange booth accommodates almost any pair of personalities.
The clips below are trend videos shared by creators on TikTok and made with other apps.
Turn yourself and your partner into a stylish rap duo for an anniversary, date night, or birthday surprise. Trading verses in the orange booth makes an unexpected, humorous gift that friends and family love watching.
Bring your favorite inside jokes to life with your best friend. Step under the hanging studio mic to see who delivers the bold opening verse and who drops the sharper closing response over the beat.
Pair a parent with a toddler, teen, or grown child. Putting family members in the booth to trade rap bars is a fun, playful take on the orange booth trend that brings laughs to family group chats and social feeds.
This example pairs a pet parent with her golden retriever.
Put your dog or cat into the booth alongside you, or place two pets head-to-head. An upright portrait lets you turn everyday pets into expressive hip-hop performers trading bars over a heavy beat.
If your generated video does not match what you expected, these practical adjustments resolve the most common issues.
Fix: Likeness issues occur when the source photo is blurry, low resolution, or covered by sunglasses, hats, or heavy beauty filters. Re-upload a crisp, high-resolution portrait with direct eye contact, clear features, and balanced natural light.
Fix: The performer on the left always starts the rap, and the performer on the right answers. If your subjects appear in the wrong order, click the Swap button in the generator before rendering, or swap your uploaded files.
Use a photo that includes the full head, shoulders and upper body. A tight face crop gives the model less information for the standing performance.
Fix: Photos where pets are lying down, curled up, or facing away lack the posture needed for the booth performance. Choose a photo where your pet is sitting upright facing forward so their chest, neck, and head align with the hanging microphone.
Fix: Unreadable files or server connection drops can cause a render to fail. If a render fails, your credits are returned automatically to your account balance. Verify that your upload is a valid JPG or PNG under 10 MB and try again.
Choose a resolution and see the fixed credit cost before you generate.
Every Hotel Lobby video is 15 seconds long. Choose 480p for 60 credits or 720p for 80 credits. The full 15-second reference and its original audio are included in that price.
Credits are deducted when generation starts and refunded if it fails. One-time credit packs cost $9.90 for 100 credits, $29.90 for 360 credits, or $69.90 for 900 credits. Pack credits never expire.
Visit Genjutsu AI pricing to buy a one-time credit pack.
| Length | 480p | 720p |
|---|---|---|
| 15 seconds | 60 credits | 80 credits |
Find clear answers to common questions about photo requirements, credits, audio matching, and creating your Hotel Lobby AI video.
Upload two separate portraits or one photo of two people standing side by side. Choose 480p or 720p and press Generate Video. Every clip is 15 seconds long and includes the original reference audio. Play and download the finished MP4 in My Work.
Each finished Hotel Lobby AI video uses the original audio from the reference performance. The model generates the picture only, then Genjutsu AI adds that reference audio to the completed MP4.
A 15-second video costs 60 credits at 480p or 80 credits at 720p. New accounts receive 10 sign-up credits. Buy a one-time credit pack to add more; pack credits never expire. Failed generations are refunded automatically.
You can provide either one photo or two photos. In single-photo mode, submit one image that clearly captures both individuals standing side by side from the waist up. In two-photo mode, upload two separate portraits—one for the left performer and one for the right performer. Files can be in JPG or PNG format up to 10 MB each. If you put people in the wrong spots, click the swap button before generating.
Yes. Upload a clear photo of your dog or cat for either performer. Upright, front-facing photos with the face and upper body visible make it easier to match the performance.
Generation usually takes a few minutes. Every output is 15 seconds long; processing time varies with resolution and server load. You can leave the page and return to My Work to play or download the finished MP4.
Likeness depends on the clarity and framing of your uploaded photo. If your face looks distorted or generic, the original photo was likely blurry, taken from an angle, or shadowed by hats, glasses, or low lighting. For the best result, upload a sharp, front-facing portrait taken in even light with a neutral or smiling expression. Clear photos from the chest or waist up give the system the clearest facial details for the video.
Yes. If you want to recast your own custom video instead of using the orange Hotel Lobby booth, use the Motion Transfer generator on the Genjutsu AI homepage. That tool accepts your own MP4 or MOV video between 4 and 30 seconds up to 95 MB, along with one reference image. It transfers the motion and body language from your video onto your uploaded character without the fixed orange booth set.
Upload your photos to create your Hotel Lobby AI video with original beats and synced vocals in a few minutes.
Generate Your VideoIf you want to recast your own clip instead of using the orange booth, head to the Genjutsu AI video editor and try motion transfer.
