58th floor aiStart creating
58TH FLOOR AI VIDEO GENERATOR

Your duo.
One mic.

Add one photo for each performer. AI uses the photos and a motion reference to generate a new 58th Floor studio duet.

Two photos12-second video720p · 9:16
Sample photo of the first performerPHOTO 1
Sample photo of the second performerPHOTO 2

Example photos and AI-generated sample. Your result may vary.

CREATE WITH 58TH FLOOR AI01 / 03

Add your photos

Photo 1 guides the left performer; photo 2 guides the right. Clear, front-facing photos work best.

58th Floor AI12s · 720p · 9:16$8.90

By continuing, you agree to our Terms and acknowledge our Privacy Policy. See pricing and refunds before payment.

Secure payment with Waffo One-time purchase
THE TWO-PERSON SCENE

Put your duo in the spotlight.

Your two photos guide the performers’ appearance. A motion reference guides their movement, framing and timing as AI generates a new studio video with a shared microphone.

Two reference photos 12-second video Two performers
AI-GENERATED SAMPLE · TWO REFERENCE PHOTOS
THE IDEA BEHIND THE VIDEO

One microphone.
Two points of view.

A small studio setup gives both performers room to be seen. The motion reference guides the camera and the exchange between them.

01 / TOGETHER

Share the frame

Your two performers appear in the same studio scene around one hanging microphone.

02 / HANDOFF

Trade the energy

One person leads while the other reacts, then the focus shifts across the duo.

03 / YOUR VERSION

Keep it personal

The photos guide each performer’s appearance. Gestures, framing and details can vary between generated results.

Each result is AI generated, so gestures, framing and timing can vary.

Two performers sharing a microphone in illustrative artwork
HOW IT WORKS

Two photos.
One new scene.

Choose one photo for each role. Clear, front-facing photos help the model represent each person more consistently.

01
Meet the two roles

Preview the scene before choosing your photos.

02
Add one photo per person

Photo 1 guides the left performer; photo 2 guides the right.

03
Make your video

Review the price, complete checkout, and receive your generated clip.

PHOTO GUIDE

Choose clear photos.

The template is designed for two people, with one person in each upload. Good reference photos help the model keep the generated performers distinct.

01Show each person clearlyUse bright, sharp photos with each person looking toward the camera. Avoid heavy filters, sunglasses or a partially hidden subject.
02Upload separatelyPut the person you want on the left in photo 1, and the person you want on the right in photo 2. Use one person per image.
03Show more of the outfitA waist-up or full-length photo can give the model more clothing detail. The generated clothing and poses may still vary.
04Get permissionOnly upload photos you own or are allowed to use. Ask every person pictured before making an AI video based on their image.
SIMPLE, PER-VIDEO PRICING

Make one moment
your own.

See the full price before checkout. No subscription is required.

58th Floor AI12-second two-person video
$8.90

One-time payment · Two photos

GOOD TO KNOW

Before you create.

What is a 58th Floor AI video?

It is a new AI-generated studio video. Your two photos guide the performers’ appearance, while a motion reference guides the performance.

How many photos do I need?

Two clear, well-lit photos—one person per image. Use only photos you own or have permission to use.

Which person goes in each role?

Photo 1 guides the performer on the left; photo 2 guides the performer on the right. The form labels both upload slots before checkout.

How long is the video, and what format is it?

This template is configured for a 12-second vertical 9:16 video at 720p. Generation results can vary.

Will it use the reference video’s audio?

Audio is enabled during generation, and the model is guided to follow the reference video’s soundtrack. The result is AI generated, so its audio may differ from the reference. The visuals are newly generated from your photos.

Will our appearance, clothes and lip sync be exact?

Your photos guide the two performers’ appearance, but AI results can vary. Clothing, details, mouth movement and timing may differ from your photos or the motion reference.

Can I use photos of pets?

This template is designed and prompted for two people. Pet photos are not optimized for this scene.

Will my video look exactly like the sample?

The sample shows the template’s general scene and pacing. Your video is generated from your photos, so its details may vary.

When will I be charged?

You will see the price before checkout. Payment is required only when you confirm your order.