How to Make a Hotel Lobby AI Video: Step-by-Step Guide

Most Hotel Lobby videos are made in one of two ways: a template app that swaps your subjects into the original COLORS clip, or a text-and-reference prompt in an AI video generator. The template route is faster and follows the original timing closely. The prompt route gives more control but takes more attempts. This guide covers both, using what the tools and press reports actually say.

Step 1: Get the right photos

XXL says the easiest method is to upload two clear, front-facing photos. LightX's guide adds three practical rules: use one photo per person or pet, prefer full-body shots, and avoid a single group photo because the tool struggles to separate the identities. Cropped waist-up photos limit how natural the staging looks. Sharp phone photos in good light are enough.

Only use photos of yourself or people who have agreed. See the copyright and safety guide.

Step 2: Pick a method

Template app. Apps named in coverage include Starrd, Summrs and LightX. XXL reports Starrd charges $5 per 15-second video. LightX says its template works from a stored reference motion video with the original audio and applies a face and body swap. Creators are also sharing free CapCut templates, and TikTok tutorials mention CapCut, PixVerse and Glorify.
Prompt-based generator. You give an image-to-video model your two photos and describe the booth, camera and movement. See the prompt guide for the structure.

Prices and free credits change often, so check the tool's own page before paying. The tools page compares what is known.

Step 3: Generate the clip

With a template, upload the two photos, choose the Hotel Lobby template and generate. With a prompt, keep the camera locked and ask for a vertical 9:16 clip of about 15 seconds. Ask for consistent faces and no camera movement, since a moving camera is the fastest way to break the effect.

Step 4: Check the result

Look for these common problems before posting:

Both people moving in exact unison. The original is a back-and-forth where one leans into the mic while the other bobs or ad-libs.
Faces drifting or merging between frames.
Hands with extra or missing fingers, especially when pointing.
Lip movement that does not match the audio.

If the result is off, change the photos first. Better-lit, sharper images fix more problems than editing the prompt.

Step 5: Export and label

Export vertical 9:16 for TikTok, Reels or Shorts. LightX says these platforms require AI-generated content to be labeled, so use each platform's AI label or disclosure option and check its current rules. Music rights on the audio are separate from the AI tool's license. For more, read the consent guide.

A shorter version of this workflow is at the quick guide, and the background on the trend is on the homepage.

Practical points

Use this topic as part of the wider Hotel Lobby AI workflow: identify the original reference, decide what changes, generate a short test, inspect faces and motion, then check consent, labeling and platform rules.

Separate the 2022 source performance from newer AI-generated clips.
Use clear reference images and consistent framing.
Inspect hands, faces, lip movement and identity drift.
Use current platform disclosure controls where applicable.
Do not use private people's images without appropriate permission.

Follow Us