How many images do I need?

Use one uploaded image. Follow the route-specific photo guidance above; for a duo effect, the single image should contain both authorized adults.

Does the generated video include sound?

No. Text2Vid renders this effect as a muted video. Add sound later in TikTok or Reels only when you have the required rights.

What photo works best?

Choose a sharp, well-lit photo that follows the framing guidance above. Keep every required subject visible, and use only an image you are authorized to upload.

Can I use someone else's, a celebrity's, or a child's photo?

Only use your own photo or an image of an authorized adult. Do not upload minors, celebrities, or private images without permission.

Smalltown Boy AI Dance Video Generator

Name: Smalltown Boy AI Dance Video Generator
Description: Upload one photo of two people and turn it into a Smalltown Boy reaction and dance video. Two portraits, one playful scene.

Upload one photo of two people and turn it into a Smalltown Boy reaction and dance video. Two portraits, one playful scene.

Example video

Bewegungs-Prompt

Edit the reference sequence described in this prompt by replacing its two main characters with the people in @image1 and @image2.

In the first frame where both original main characters appear together, identify the original character on the left as Character A and the original character on the right as Character B. Replace Character A with the person in @image1, and Character B with the person in @image2. Lock these assignments for the entire video. Track each original character through every cut, crossing, position change, occlusion, exit, and reappearance. Never swap the replacements when their screen positions change, and never blend their identities.

Use each portrait as an appearance reference for its assigned character. Replace the original character's visible face, hair, skin, body, clothing, and distinctive accessories. If a portrait does not show the full body or every clothing detail, complete the unseen parts naturally in a way that matches that person, then keep those details consistent in every shot. Do not transfer either portrait's background, pose, camera angle, or lighting into the video. Remove recognizable traces of the original characters' faces and costumes.

Make each replacement follow the exact performance of its assigned original character: the same movement path, body actions, dance choreography, gestures, head turns, gaze direction, facial-expression timing, lip movements, interactions, and timing with the music. Preserve the original blocking and contact with props and other people, while adapting the replacement's proportions naturally.

Preserve the source video's scenery, background, props, other people, composition, framing, camera movement, cuts, lighting, visual style, duration, aspect ratio, and playback speed. The video is muted. Do not retain the original audio track, music, vocals, dialogue or sound effects. Do not create new voices or change the performance.

Integrate both replacements with natural perspective, scale, shadows, reflections, occlusion, and motion blur. Maintain stable faces, hair, clothing, and character identities across every frame. Avoid flicker, morphing, duplicate people, extra limbs, identity swaps, and remnants of the original characters. Change only the two designated characters and the visual details needed to integrate them into the existing footage.

Upload one image

Drag & Drop oder Ctrl+V zum Einfügen

Upload one JPG or PNG image, up to 10 MB.

Einfache Prompts Image optional

Edit the reference sequence described in this prompt by replacing its two main characters with the people in @image1 and @image2.

Dauer

KI-Modell

Warum dieses KI-Video-Tool wählen?

Dauer 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15s

Seitenverhältnis 16:9, 9:16, 1:1, 4:3, 3:4, 21:9

Auflösung 480p, 720p

Bild(er) hochladen 2

Audio generieren Available in supported workflows

Text2Vid is an independent platform. Model names are shown for reference only and do not imply affiliation with or endorsement by Google, OpenAI, Runway, xAI, or other model providers.

Sofort mit der Erstellung von KI-Videos beginnen

Verwandeln Sie einfache Textprompts mit unserem leistungsstarken KI-Videogenerator in ansprechende Videos. Keine Bearbeitungskenntnisse erforderlich – beschreiben Sie einfach Ihre Idee und lassen Sie die KI die Arbeit erledigen.

Ihr erstes KI-Video generieren

SSL Secure Privacy Protected Commercial on Paid Plans