Connor Price Slide AI Video Generator

Photo 1 is the camera-facing performer originally wearing a striped white hoodie and blue cap. Photo 2 is the partner originally in a denim jacket and red-and-white cap, carrying the silver boombox. Their screen positions change as they walk, so assign photos by the performance roles rather than a fixed left or right position.

Use two separate images with one person in each. A sharp half-body or wider view with visible hair, shoulders and clothing provides useful detail for the moving scene. Avoid heavily blurred photos, groups and objects hiding the torso. Full-body information can help with trousers and shoes, which may become visible as the camera moves back.

Each photo guides the complete person, including hairstyle, body proportions, clothing and accessories. The source caps and jackets identify the two roles; they are not required clothing for your input. The silver boombox remains the reference prop. Unseen outfit details still require interpretation, so inspect both characters throughout the result.

The template retains the silver boombox from the source performance. There is no third upload slot for a replacement speaker, logo or other object. You choose the person carrying it. If you need a different prop or scene, start from the Motion Transfer homepage with a reference video suited to that task.

The completed video includes the reference sound and follows the visible mouth movements. A photo does not supply a new recording of that person’s voice. This page has no lyrics editor, microphone input or song selector. Listen to the preview to confirm the version you want, and review the finished result with sound.

This page uses the prepared street sequence for approximately 21 seconds. It keeps the red-brick setting, backward-moving camera and two-person interaction. There are no separate duration, background or aspect-ratio controls for the fixed template. Output resolution changes do not select a different performance.

Review the lead’s hands, sliding footwork and mouth movements, then check the carrier’s shoulder and fingers around the boombox. Look for clothing drift, intersecting arms or changes in the prop as the two people move close together. The instructions request consistent roles and motion, but the model can interpret fast movement or occlusion imperfectly.

Motion Transfer provides an independent AI adaptation of the supplied reference. The name helps identify this street-duet format and does not imply an artist partnership or endorsement. Use photos you have permission to edit, present the result as AI-generated, and check the footage and soundtrack rights needed for sharing or commercial use.