Skip to content
burningbridgesAI
My creationsPricing

Smalltown Boy AI Video Generator

Photo 1 is the foreground figure on the left at the opening. Photo 2 is the figure behind and to the right. The street scene stays in place.

Create a video

Foreground · Photo 1
Background · Photo 2

By generating, you confirm media permissions and accept the Use Policy.

Open library ↗

A closer figure and one behind

Smalltown Boy AI casts two people into a performance that already has depth. Photo 1 is the foreground figure on the left when the clip opens. Photo 2 is the background figure to the right. Each photo brings a face and an outfit. The fence, the plants, the ground, and the street stay in the scene. You need permission for both people. This page is not affiliated with the recording, and it is not a song-rights or artist partnership. Custom prompt or custom video work goes to /video.

Community duo with a foreground figure and a second figure behind

Assign the near role, then the far one

  1. 01

    Upload the closer figure first

    Photo 1 is the person in front, on the left, at the opening. Show one face and the outfit that should read at close range. Do not put both people in this frame.

  2. 02

    Give the farther figure a second photo

    Photo 2 is the person who starts behind and to the right. Use a different appearance so the depth stays readable. Then set a resolution. Credits follow that resolution. This page has no prompt field.

  3. 03

    Watch the depth change without a role swap

    Play the result through the opening, the later shared frames, and the approach toward the camera. Each photo should stay with its own figure. The performance soundtrack is restored from the source. This page is not affiliated with the recording.

Two depths in Smalltown Boy AI

Place the closer figure first

At the opening, the foreground figure stands on the left and nearer the camera. That role is Photo 1 for the whole performance, not only for the first second. Because this person fills more of the frame, the face and the full outfit need to be easy to see in the file. Use that opening frame as the first check that the nearer person is the one you assigned, before the second figure comes forward.

A turned-away snapshot or a crop at the neck makes the closest role the weakest one. You do not have to photograph anyone outdoors or in front of a fence. The scene already has its place. The photo’s job is the person you have permission to feature and the clothes they should wear up close.

Give the farther figure a separate photo

Photo 2 starts in the background, to the right of the closer figure. It is a second identity, with its own face, hair, build, and clothes. Distance in the opening does not make this role optional. The same person comes forward later, and a muddy portrait will show.

Do not hide Photo 2 inside the first upload. Two people side by side in Photo 1 do not become the foreground and background cast. If the two outfits are almost the same and the faces are unclear, the depth is harder to read. Distinct clothes make the far figure easier to keep track of once the shot tightens.

Community cat duo in the foreground and background places

Depth changes, and the assignments do not

The two figures trade visual weight as the performance goes on. One moves forward, the other sits farther back, and they also appear together. Those moves belong to the scene. Your assignments do not follow the new depth. Photo 1 stays with the figure who opened in front on the left. Photo 2 stays with the figure who opened behind on the right.

When they dance side by side, Photo 1 remains the left figure and Photo 2 remains the right figure. The final approach toward the camera keeps that same pairing. If the faces trade places when the depth trades places, the cast has slipped. Check the opening, the side-by-side passage, and the approach as three separate moments.

Keep each outfit attached to its role

Clothes travel with the photo, not with the position in the frame. The jacket on Photo 1 should still be that jacket when the closer figure is no longer the only person in front. The clothes on Photo 2 should still belong to the background figure after that person comes nearer.

Show the outfit you mean, including enough of the body to judge the cut and the color. Fine text and small pins can shift. A full, plain shape is easier to recognize across 21 seconds of movement than a detail that only exists in a still portrait. Neither figure should inherit the other figure’s clothes.

Community dog duo keeping the two depths apart

Fence, plants, and ground remain

The scene already holds the fence, the plants, the ground, and the street around the two figures. Your photos are not background plates. A living room behind your subject does not replace the fence, and a studio sweep does not remove the plants. The camera path and the lighting of the performance stay as well.

You also cannot add a third dancer by leaving someone in the photo background. The performance is built for these two roles. Extra faces in an upload compete with the role you meant to assign. If the street itself is the wrong setting, write that other scene at /video.

This page is not a recording partnership

This page is not affiliated with the recording. It is not a song-rights partnership, and it is not an artist partnership. Casting two figures into the scene does not mean an artist, a label, or a publisher made, approved, or sponsored the result. No caption and no photo choice on this page creates that relationship.

Say that plainly if you share the clip somewhere the title could be misunderstood. The product name refers to this scene on Burning Bridges AI. It is not a badge of permission from the people who made the recording, and it does not appoint you to speak for them.

Opening frame with the closer figure on the left

Restored sound is not a rights grant

What plays with the picture is the performance soundtrack, restored from the source, so the two stay together. You do not upload a replacement song. Restoring that soundtrack is not a license, not a sync grant, and not a statement that the recording is yours to republish.

The two portraits also do not become the original performers. Mouth movement and timing follow the scene that already exists. Listen to the full clip, about 21 seconds, and decide whether your planned use is covered by rights you actually have. If that use needs a different track, this scene is the wrong place to look for one. The page cannot supply those rights.

Permission and resolution before you generate

Permission is required for both uploaded people. Consent for one friend does not cover the other, and a photo copied from a public page is not consent. Character images are appropriate only when you are allowed to use them. Keep each file to a single subject.

Credits follow the resolution selected in Settings. The estimate changes with that size, so read it after you choose and before you generate. A larger file will not correct a swapped foreground. Fix Photo 1 or Photo 2 first. Finished clips remain in your creations for another look without a new request.

Frame of both figures in the street scene

Smalltown Boy AI: your questions answered

Which Smalltown Boy AI photo is closer?

Photo 1 is the foreground figure on the left at the opening. Photo 2 is the background figure to the right. Those assignments stay with the same figures when the depth changes. In the side-by-side dance, Photo 1 is still on the left and Photo 2 is still on the right.

Can I add someone behind them?

No. The scene has two roles. A third person in either photo is not a new dancer, and the fence, plants, ground, and street are not upload slots. Use two clear portraits of people you have permission to feature.

Is this page affiliated with the recording?

No. This page is not affiliated with the recording. It is not a song-rights partnership and not an artist partnership. Creating a clip does not mean the recording’s makers endorsed the result or gave you publishing rights.

How long is Smalltown Boy AI?

About 21 seconds. The opening depth, the later pairing, and the approach toward the camera are inside that length. There is no duration control. Watch the whole file before you decide the two identities held.

Where does a prompt of my own go?

Take a prompt of your own, or a video you want to build from scratch, to /video. This page has no prompt field. It will not replace the street, add a third figure, or renegotiate anything about the recording.

Do credits change with the picture size?

Yes. Credits follow the resolution you select in Settings. Read the estimate for this scene after you pick a size. The soundtrack restored from the source does not add a separate audio charge, and it still does not grant rights in the recording.

Build your next creative idea

Burning Bridges AI →

Cast the lead and optional background characters in our signature performance.

AI Image Generator →

Create or refine a character portrait before bringing it into a trend.

AI Video Generator →

Explore a different scene with your own prompt and reference images.

Cast the two figures in Smalltown Boy AI

Closer on the left, farther on the right, each with a permitted photo and a visible outfit. The street stays. This page is not affiliated with the recording. Check the resolution estimate before you generate.

Try Smalltown Boy AI