Hotel Lobby AI Prompt Examples: Pets, Solo and Characters

These examples build on the five-part structure in the prompt guide: format, setting, identity, motion and constraints. They are written for this site, not copied from a tool, and are meant for general image-to-video models where you upload reference photos. Template apps do not need prompts.

Pet and owner

Vertical 9:16, 15 seconds, static camera, no cuts. Solid orange studio wall, one microphone hanging at center. Use reference image 1 for the person on the left and reference image 2 for the dog on the right. The dog stands upright on its hind legs in a human-like pose. The person leans toward the microphone first while the dog nods. Around the middle they swap, and the dog leans in while the person steps back. Faces and fur stay consistent. No zoom, no camera movement, no merged bodies.

Why it works: it names the pose in plain words, which is what LightX says its template does automatically for animals.

Solo version

Vertical 9:16, 15 seconds, static camera. Solid orange wall with one hanging microphone. Use the reference image for the single performer, centered next to the microphone. The performer leans in for the first half, then steps back and bobs before leaning in again at the end. Keep the face consistent. No camera movement.

Why it works: one subject reduces the chance of merged identities, and LightX notes that some creators post solo versions.

Cartoon or fictional pair

Vertical 9:16, 15 seconds, static camera. Solid orange wall with one hanging microphone. Use reference image 1 for the left character and reference image 2 for the right character. Keep each character in their original art style. The left character leads, the right character reacts, then they swap. No blending between the two styles.

Why it works: stating the art style prevents the model from turning both characters into realistic humans.

Useful constraint phrases

"Locked camera, no zoom, no pan."
"Faces stay the same for the whole clip."
"Natural hands with five fingers each."
"No text or logos on screen."
"Keep the orange wall a solid, even color."

What not to add

Do not paste the song's lyrics into the prompt. They are copyrighted, and asking a model to lip-sync them raises separate rights questions. See copyright and safety. For two-person specifics, read the two-person guide.

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