Vismuse

58th Floor AI — Teal studio rap duet

Put yourself and a friend at the same hanging microphone. The opening left performer finishes the hook, then the right performer takes the verse and the close-up. Two separate photos define two recognizable roles.

Create my video

Pick an effect

All 136 effects
0 / 3000

Paid credits required. Check the cost before generating.

Reference preview
Reference footage showing the intended scene. Your video is generated from your uploaded photos.

What is 58th Floor AI?

58th Floor AI turns the teal-studio rap handover into a two-photo video. The scene is recognized by its bare turquoise room, silver suspended microphone and contrast between the performer delivering a line and the partner listening. A medium two-shot leads into the right performer’s close-up, a full-body platform view and a closer exchange between both roles. The photos define your cast rather than borrowing the source performers’ faces, hairstyles or costumes.

Reference footage showing the intended scene. Your video is generated from your uploaded photos.

Your photos and the scene

The prepared motion clip guides the handover, physical gestures, camera drift and cuts. Photo 1 stays the opening left hook performer; photo 2 stays the right verse performer even when only that face fills the frame. Keep both uploads distinct. The teal studio is the default; an optional instruction can change lighting, clothing or setting while preserving these roles. No video upload or prompt writing is required.

Create my video

  1. 01

    Add your photos

    Upload two separate, sharp photos with one subject in each. Show the face, hair and outfit clearly, ideally from the knees up or full body. Avoid group pictures, hidden faces and tightly cropped arms. Put the person who should get the verse and close-up second. Different outfits help the two identities stay readable in wide shots.

  2. 02

    Personalize the scene

    The prepared motion clip guides the handover, physical gestures, camera drift and cuts. Photo 1 stays the opening left hook performer; photo 2 stays the right verse performer even when only that face fills the frame. Keep both uploads distinct. The teal studio is the default; an optional instruction can change lighting, clothing or setting while preserving these roles. No video upload or prompt writing is required.

  3. 03

    Generate and download

    Review the displayed cost, then generate. Check faces, hands, motion and sound before downloading. New generations and revisions use paid credits.

58th Floor, COLORS-style duet or Hotel Lobby?

This is the teal-studio hook-to-verse exchange associated with 58th Floor. Hotel Lobby uses a different orange-room performance. Choose this scene for the hanging-mic duet and right-side close-up. It creates a short personalized visual performance, not a complete song or a clone of your voice.

Make it your way

The template is built in. Use the ready-made scene, or add a short instruction to make it yours.

Ready to try it? Upload and generate.

Upload two separate, sharp photos with one subject in each. Show the face, hair and outfit clearly, ideally from the knees up or full body. Avoid group pictures, hidden faces and tightly cropped arms. Put the person who should get the verse and close-up second. Different outfits help the two identities stay readable in wide shots.

No prompt needed. Leave the optional instructions blank to use the included template.

Make your video

Have something specific in mind?

Describe the clothing, lighting or setting you want in the optional instructions. A short, specific request is enough.

For example
Keep our faces and outfits. Use warmer studio lighting, retain the teal backdrop, and keep photo 2 in the verse close-up.

2K is available on eligible plans and uses more credits than 768p.

Questions about this video

How many photos do I need?

Upload two separate, sharp photos with one subject in each. Show the face, hair and outfit clearly, ideally from the knees up or full body. Avoid group pictures, hidden faces and tightly cropped arms. Put the person who should get the verse and close-up second. Different outfits help the two identities stay readable in wide shots.

Do I need to upload a reference video?

The prepared motion clip guides the handover, physical gestures, camera drift and cuts. Photo 1 stays the opening left hook performer; photo 2 stays the right verse performer even when only that face fills the frame. Keep both uploads distinct. The teal studio is the default; an optional instruction can change lighting, clothing or setting while preserving these roles. No video upload or prompt writing is required.

Does the video include sound?

The matching soundtrack is added when sound is enabled. Request a silent video to leave it out.

How long is the video?

14 seconds, vertical 9:16 MP4. Sound is optional; exact lip sync is not guaranteed.

Can I change the outfit or background?

Yes. Add a short instruction about clothing, lighting or the setting. Keep the assigned photo roles for the selected scene.

Create my video

Upload two separate, sharp photos with one subject in each. Show the face, hair and outfit clearly, ideally from the knees up or full body. Avoid group pictures, hidden faces and tightly cropped arms. Put the person who should get the verse and close-up second. Different outfits help the two identities stay readable in wide shots.

Create my video

Explore more video trends

On The Radar AI Video GeneratorTiny Desk AICheck One Check Two AI