The orange-booth duo format

Hotel Lobby AI Video.
Your duo. Your take.

Upload two photos and put your duo in the orange booth. We provide the performance reference and direction; choose 7, 10 or 15 seconds, then generate with one click.

Two photos · 7–15 seconds · Login + paid plan or pack required

Made with TaleScene · MiniMax H3 · 7-second portrait demo. Play with sound.

Cast the scene

Make your Hotel Lobby AI video

Choose one photo for each performer. Left and right roles are fixed by the upload slots. No prompt, script or storyboard confirmation is needed.

01

Choose your duo

One person per photo. Left and right set their place in the video.

0/2 photos
Left performer← LEFT
Right performerRIGHT →

Clear face, visible hair and outfit · JPG, PNG or WebP · Max 8 MB each

Video length
Video settings9:16 · H3 · 768p
Video settings

7-second performance with matching video and audio references. The model generates both performers for your chosen frame.

Add a photo for each performer to get started.

Login + paid plan or credit pack required. No prompt needed.

From photos to performance

How to make an orange-booth duo

01 · Upload two photos

Choose one clear individual photo for the left performer and one for the right. Both faces should be easy to recognize.

02 · Generate with one click

Sign in with a paid plan or credit pack. Choose your output format and AI model. The default is a 30-credit, 7-second vertical MiniMax H3 video. The template prepares your scene and generates automatically.

03 · Watch and download

Follow generation progress on this page, then watch your result and open it to download. Your video also remains in My Stories.

A fixed Hotel Lobby AI template

The template supplies the orange booth, hanging microphone and video + audio references matched to your selected duration. MiniMax H3 uses your photos for identity and the reference video for performance timing. You do not need to upload another video.

Choose photos that keep your duo recognizable

Use a sharp photo with one person per image, a visible face and minimal obstruction. Match the outfits you want to see in the result. Generated faces, hand movements, sound and lip sync can vary, so watch the finished clip before sharing.

Questions

Hotel Lobby AI video questions

What to prepare, what the preset does, and how paid rendering works.

What is the Hotel Lobby AI video trend?

The orange-studio duo performance features two people beneath one hanging microphone. This template uses a fixed performance reference to guide your duo’s movements.

What do I need to upload?

Two individual photos: one for the left performer and one for the right. Choose clear faces, including hair and clothing, and only use photos you have permission to use. JPG, PNG and WebP files up to 8 MB each are accepted.

Do I need to write a prompt or generate a script?

No. Upload both photos and click Generate video. TaleScene automatically prepares the scene and calls your selected AI model with the fixed performance reference. MiniMax H3 is the default; Seedance 2.5 is also available.

How long is the generated video?

Choose 7, 10 or 15 seconds, with 9:16 portrait as the default. You can choose 4:3, 16:9 or 1:1 before generating. The delivered file may differ slightly in duration. Faces, choreography and lip sync can vary.

Do I need to log in and pay?

Yes. A paid plan or qualifying credit pack is required, with 30 / 42 / 62 credits for H3 at 7 / 10 / 15 seconds. For 7 seconds, the cost is 86 for Seedance 2.5 at 720p, or 156 at 1080p. Credit packs start at $19.99; the pack price is not the price of one video.

Does it preserve the original soundtrack?

We send the reference soundtrack to the model and request a new vocal rendition of the same song excerpt, melody and beat. Audio is regenerated, so exact musical fidelity and lip sync are not guaranteed.