Maker
A maker, not a playground
Generic video generators give you an empty prompt and wish you luck. This hotel lobby AI video maker ships with the whole format preset — the solid-color booth, the single hanging mic, the verse-trading choreography, the vertical crop. Your only job is picking the two faces and hitting generate.
The hotel lobby AI video maker: two portraits in, an animated booth music video out. Four presets, vertical 9:16, free to preview.
Your video may be selected and published to the public Explore feed to inspire other creators.
Capabilities
The maker's core job: read two front-facing portraits and put those exact faces on stage. One photo per performer gives the strongest likeness; a single frame with both people works too.
Classic Orange (the trend original), COLORS Red, Rap Cypher concrete, Neon Noir haze, 90s VHS, and the DJ Booth — every preset keeps the single shared mic and the tight two-shot that make the format recognizable.
The maker animates the structure of the song: one performer leans into the mic for the verse while the other nods and ad-libs, then they swap. That call-and-response is what makes the clip feel performed, not posed.
Every render comes out in the exact framing TikTok, Reels, and Shorts want — chest-up, both performers, mic centered. No cropping, no reframing in post.
The prompt is prefilled with the booth recipe. Open the panel to change the styling, the gestures, or the booth color — or paste a prompt from the prompt library.
Watch the full render before any account or card. HD downloads and longer durations use credits, and failed renders are never charged.
Compare
You can chase this trend with a general-purpose tool. Here is what usually happens:
| Aspect | This maker | Generic generator |
|---|---|---|
| Purpose-built template | The stage, mic, framing, and choreography are preset for this one trend | You assemble the scene from scratch with generic prompts |
| Identity handling | Two-photo upload built for duo likeness | Single-image focus; duos often morph or drift |
| Output format | 9:16 vertical clip, trend-ready | Any ratio — you crop and reframe yourself |
| Time to first video | About two minutes, three clicks | Many iterations of prompt engineering |
| Audio strategy | Mute and lay the licensed song in your editor | Model audio you have to replace anyway |
Want the full parameter documentation instead? Read the hotel lobby ai video generator page.