Two photos · Left takes the hook · Right takes the verse

Two photos in, a 58th Floor duo out

58th Floor AI needs exactly two photos. Photo 1 is the person on the left of the hanging mic who finishes the hook; photo 2 is the person on the right who takes the verse and gets the close-up. Use two separate, clear, front-facing pictures: one group selfie of you both usually blurs the faces together.

Updated

By the 58th Floor AI editorial team · How we check these guides

01 · Add the two rappers

Two photos: left takes the hook, right the verse.

0/2

One clear adult or pet per photo, face visible. Separate selfies are fine. JPG, PNG or WebP, 10 MB max, 300 × 300 pixels minimum.

02 · Choose your video
Model
Quality
Audio
Director’s notes Optional Outfits, sunglasses or a prop. The studio, shots and lip sync stay fixed. 0/500

The original “58th Floor” sound is kept by default; it contains explicit language. Pick Silent to export the clip with no soundtrack.

10 credits · Seedance 2.0 Fast · 15s · vertical MP4 · See pricing

What's new on this page

  • First version: the two photo slots, how to choose who goes first, photo checklist and duo ideas.

Photo 1 and photo 2 at a glance

Photo 1Photo 2
Place in the studioLeft of the hanging micRight of the hanging mic
PartRaps the end of the hook in the opening shotTakes the verse and raps to the end
Close-upNo, stays in the two-shots and the wideYes, the close-up from 5.5 to 8.7 seconds
While the other rapsVibes, dances and nods, mouth closedListens with mouth closed during the hook
Best photo to useAny clear, front-facing photoYour sharpest, best-lit face

How every 15-second clip is staged. Generated video varies from render to render.

Why two separate photos work better than one

The generator reads each face from its own picture and keeps that person on their side of the mic for the whole clip. When both people share one image, the faces are smaller and the model has to separate them, which is where features start to mix and the two people get mixed up between cuts.

The photos do not need to be taken together, on the same day or in the same light. Two ordinary selfies are enough. If the only good picture you have is a photo of the two of you, crop it twice so each person has their own image.

Who should be photo 1, and who photo 2?

Give photo 2 to whoever should steal the show: they rap most of the clip and get the close-up. Photo 1 opens with the hook and spends the rest of the clip reacting, which is often the funnier role for the friend who never takes anything seriously.

If you plan to make two clips, swap the photos the second time. Posting both versions side by side is a common way people use the trend.

What makes a good photo

One person (or one pet) in the frame, face clearly visible, front-facing or a slight angle, chest-up or closer. Even daylight beats a dark room. Remove sunglasses, masks and anything covering the eyes, and skip heavy beauty filters.

What you wear in the photo is what you wear in the clip, shoes included on the wide shot. Use photos you own or that the other person agreed to share. Photos of minors, celebrities and public figures are not allowed.

Duo ideas for the 58th Floor

Best friends: the classic version, one confident hook and a friend who takes over the verse. Partners: an easy anniversary post. Siblings: settle a family rivalry as a studio face-off. A parent and grown-up child: the surprise of seeing your dad take the verse. Coworkers: a launch-day clip for the team channel, if everyone agreed to it.

You and your pet also works: put your dog or cat in either slot and it raps at the mic with its real paws.

06 · FAQ

Questions about 58th Floor AI

No. Two separate selfies taken anywhere work. Each person is placed in the teal studio from their own photo.

No. The format is a duo: one person on each side of the hanging mic. For a group, make several clips with different pairs.

Yes. Either slot can be a dog or cat, or both can be pets. The animal keeps its real paws and mouth; no human hands are added.

Crop it into two images, one face each, and upload them to the two slots. A single photo with two faces is the most common cause of blended or mixed-up faces.

No. Only photos of people who agreed to appear, and no celebrities, public figures or minors. That includes Anderson .Paak and Cordae.

Who takes the hook, and who takes the verse?

Add two photos, check the price on the button and get your 15-second 58th Floor AI clip in a few minutes.