Two-person performance video

Turn two portraits into an original Hotel Lobby-style AI video.

Upload one photo for each performer, choose a supported video model, and generate an original orange-booth duet with optional lyrics, music direction, and performance notes.

A local video example used to explain a short performance workflow.
Start with
Two separate performer photos
Create
A short original duet video
Customize
Music style, lyrics, and direction

Examples to inspect before you generate

Inspect different image directions before choosing a model, frame, and prompt structure.

Every card identifies whether it is a verified model-family example or a visual reference. Reference cards are not model benchmarks or before-and-after claims.

Editorial poster showing clothing draped over a blue chair on a pale background.

Poster composition

One central object, clear negative space, and a deliberate text hierarchy.

Verified model-family example

Verified GPT Image family example from the local ImagineClip prompt library.

An isometric miniature landmark scene on a floating base with a simplified landscape.

Illustrated place concept

Combine a place, its defining landmarks, and a clear viewing angle in one visual direction.

Verified model-family example

Verified Nano Banana family example from the local ImagineClip prompt library.

A sculptural food-based typographic composition on a wooden serving board.

Concept-led object treatment

Give an abstract idea a material, a physical form, and a simple composition rule.

Verified model-family example

Verified GPT Image family example from the local ImagineClip prompt library.

[01]

What this focused workflow controls

01

Left and right performers

The first photo stays on the left and the second photo stays on the right.

02

An original orange-booth scene

The template adds a hanging microphone, locked framing, and a two-person performance direction.

03

Optional creative direction

Add original lyrics, a music style, or a short director note without writing a full prompt.

[02]

How to make the video

Start with the two photos. Everything else has a useful default and can be adjusted when you want more control.

  1. 01

    Add two authorized photos

    Use one clear person or pet per image and decide who should perform on the left and right.

  2. 02

    Choose a model and style

    Select a supported video model, frame, and optional music direction. The price follows the selected model settings.

  3. 03

    Add original lyrics if you want

    Lyrics and director notes are optional. The template turns them into performance guidance.

  4. 04

    Generate and review

    Play the finished clip, check both identities and motion, then download the MP4.

[03]

Before you generate

01

Use original text and audio direction
Do not submit lyrics, recordings, or identities you do not have permission to use.

02

Generated audio is model-dependent
Audio and mouth movement can vary by model. This workflow does not promise word-level lip-sync.

03

Review the final clip
Faces, hands, clothing, positions, and timing can drift during generation.

[04]

Hotel Lobby AI video FAQ

How many photos do I need?
Upload two separate photos, one for the left performer and one for the right performer.
Do I need to write a prompt?
No. The scene and performance direction are built into the template. Lyrics and director notes are optional.
Can I add lyrics?
Yes. Add original lyrics for the left performer, right performer, or a shared chorus. The model may not reproduce every word exactly.
Will the video include music?
Models that support generated audio can create sound when audio is enabled. You can also choose a silent output and add licensed music later in your editor.

Updated:

Capability source: Current ImagineClip video-generation workspace.

Create a Hotel Lobby video