KagentenA Hotel Lobby AI video puts you and a friend into the viral "Hotel Lobby" rap performance — the duet filmed in an orange studio, hanging microphone and all. You upload two photos, one per performer, and the AI returns one continuous rap clip in the template's orange-studio scene. Pick 5, 10 or 15 seconds, portrait or landscape, and either keep the built-in rap track or write your own lines for the two performers to rap in their own voices.
This guide is written by the team that built the template, from our own test generations — including the custom-lines feature. Below: what the video looks like, how the two-photo casting works, how to write lines that survive the take, and what it costs.
Ready to make yours? Open the Hotel Lobby tool — you'll sign in first so the photos and video stay in your account.
Both performers are cast from your two photos — each person appears as they look in their picture, outfit included — inside the trend's orange-studio scene with the hanging condenser microphone between them. The clip runs as one continuous take, and you choose:
One honest note on likeness: the template casts the people from your photos, it does not paste the photos in. Photos, avatars and cartoon characters all work — here is the same template running on two illustrated characters, each keeping their own cartoon look:
Each person appears exactly as in their photo — outfit included. The rules that matter:
This is the feature that makes the template more than a filter. By default the video ships with an original, AI-composed rap track built for this template — custom-made, so it is safe to post anywhere with no copyright claims. If you write your own lines, the performers rap your words instead: each in their own voice, in whatever language you write.
What we learned testing the feature:
It depends on the length you pick: 5-second videos are usually ready in 5–10 minutes, 10-second videos in 10–15, and 15-second videos in 15–25 minutes. You can close the page while it works — the video keeps processing and appears in My Videos when it's finished.
Pricing: from $4.9 per video — 5 seconds $4.9, 10 seconds $6.9, 15 seconds $8.9 (normally $9.9) — or pay with credits from any credit pack. Images and videos share one credit balance, and there is no subscription. A failed generation refunds the credits automatically — you only ever pay for a video that's delivered.
| Hotel Lobby | Burning Bridges | |
|---|---|---|
| Best for | A duet with a friend — or a rap battle with yourself | A solo star moment at a fancy party |
| Photos needed | 2 — one per performer | 1 |
| Custom lyrics | Yes — replace the track with your own lines | No — music is baked in |
| Length · quality | 5, 10 or 15 s | 15–20 s · 1080p |
| Price | From $4.9 (200–500 credits) | $8.9 (500 credits) |
Both live on Kagenten: Hotel Lobby for the two-person rap duet, Burning Bridges for the one-photo party scene. Prefer the solo route? Our Burning Bridges AI video guide covers it step by step.
Yes. Kagenten runs entirely in the browser, so any modern phone browser (Safari, Chrome) works — upload both photos from your camera roll, pick a length, generate, and download the finished video without switching to a computer.
No app is needed. Everything happens on the web page: upload two photos, tap Generate, and the video is saved to your account. There is nothing to download or install.
No — two photos of the same person work fine (different outfits make the duet read better). There's no requirement that the performers be different people.
By default the video ships with an original, AI-composed rap track built for this template — custom-made for it, so it is safe to post anywhere. If you write your own lines, each performer raps your words in their own voice, in whatever language you write. Keep the lines short for a clean take.
Yes. The file is watermark-free and ships with the sound built in. Portrait output is made for short-video feeds; landscape fits YouTube and wider screens. You own what you generate and may use it commercially.
From $4.9 per video: 5 seconds costs $4.9, 10 seconds $6.9 and 15 seconds $8.9 (normally $9.9). You can also pay with credits from any credit pack. No subscription, and every failed generation is refunded automatically.
No. This template is an independent, fan-made creative work for entertainment — not affiliated with, endorsed by, or sponsored by any artist or label. Only upload photos of people who have agreed to appear.
This guide was written by the Kagenten team on 2026-10-13, based on our own live test generations with this template (screenshots and clips are real product outputs; the text was drafted with AI assistance and reviewed by the team). Questions we didn't cover? Contact us — or start from the Hotel Lobby tool page.