The orange room.
Matte orange wall and floor. No furniture, no distractions. A simple set with an unmistakable color.
Two photos in, one orange booth rap duo out — vertical 9:16, no editing.
Preview your photos locally. Generation and checkout are not available yet.
Photos stay in your browser until you choose to generate.

The Hotel Lobby AI trend takes its name from Quavo & Takeoff’s song. The orange COLORS performance set gives it the look.
Matte orange wall and floor. No furniture, no distractions. A simple set with an unmistakable color.
A black microphone suspended between both subjects. It ties two separate faces into one performance.
One person performs while the other nods and waits; then they exchange. Keep the left and right references clear.
A steady full-body shot in vertical 9:16. Leave space around the duo, with both faces visible.
Choose one clear, front-facing photo per person. Separate references keep the two roles distinct.
Place one photo on the left and the other on the right. The scene is set: orange walls, one hanging microphone, vertical 9:16.
Choose a paid pack, generate when the service is ready, and review both identities. Add an authorized sound in your publishing app.
Original scene concepts.
Illustrations, not generated videos.
DUO IDEA / 01Same booth. Different energy.
DUO IDEA / 02Your favorite person, on the other verse.
DUO IDEA / 03A little unexpected. Very memorable.
| Workflow | What you bring | What it handles | What to check |
|---|---|---|---|
| Hotel Lobby AI | Two separate photos | Dedicated orange-booth scene, 9:16 | Paid packs; generation is being configured |
| Higgsfield Genjutsu | Source video + reference images | Edits based on the source performance | Current account access and credits |
| TikTok / Reels sound tools | Your finished visuals | Adds an available authorized sound | Availability, region and usage terms |
It comes from Quavo & Takeoff’s Hotel Lobby performance in the orange COLORS booth. The trend puts two faces into that booth so they trade bars at one hanging mic.
Pick who is on the left and who is on the right, upload one clear front-facing photo for each, and choose a video pack. The intended output is a vertical 9:16 clip. Generation is currently being configured.
Separate photos give each person a clear reference and make left/right instructions easier to follow. A group photo makes the model guess. AI can still change faces or swap positions, so always review the result.
Unexpected duos are part of the trend — two pets, a couple, or a family pairing. Use photos you have permission to use, and review the result: animal and baby references may be interpreted less reliably.
Upload one photo per person, assign each to a side, and check the result: booth color, hanging mic, and left/right identity. Clear references reduce ambiguity but do not guarantee stable faces.
No subscription. One video credit per generation.
1 video credit · one-time payment
3 video credits · one-time payment
10 video credits · one-time payment
Payment and generation are being configured. No purchases are accepted yet.