Take the front spot in a street performance. Uptown Funk AI uses one photo for the lead’s complete look and outfit while keeping the supporting group and reference sound.
Explore examples of this effect. Open a video for a closer look.
Uptown Funk AI makes the street-performance remake shown above from one person photo. The front lead moves with a supporting group through coordinated steps, shoulders and arm gestures. Your image defines that lead’s complete appearance and clothing; the background performers remain part of the scene. This Uptown Funk AI page follows a twelve-second prepared sequence with its camera cuts and source sound. It gives you a quick way to place a chosen character at the front of a group performance without assembling a cast or filming a dance.
The action is prepared. Choose the cast and review your settings.
STEP 1
Choose one adult in a clear full-body photo. Show the hairstyle and intended outfit, including shoes. Avoid several people competing for attention in the same image.
STEP 2
Select Economy, Standard or Original, then an available resolution. All modes follow this same short reference, with a 12-second output setting. Review the credit quote on Generate and sign in before submitting.
STEP 3
Open the finished clip in My creations. Follow the front lead across every cut. Check hands, clothing, lip movement and overlap with the supporting performers, then listen to the final audio with the video playing.
Reference frames show key moments in the prepared performance.
Uptown Funk AI separates one editable role from the supporting cast. Upload the person who should lead at the front; you do not need pictures for the dancers behind. Their placement helps the movement read as a group performance. Uptown Funk AI replaces the lead’s whole look, including hair and outfit, while asking the model to retain the surrounding people and setting. A group photo will not assign new identities to everyone in the video.
The street scene in Uptown Funk AI gives the lead’s clothing room to be seen through steps and upper-body gestures. Choose a full outfit in the same person image: jacket, trousers and shoes can define a different character without changing the dance. There is no separate wardrobe slot. Uptown Funk AI carries that image across the cuts, although fine patterns, logos and small accessories may change as the pose and viewpoint shift.
Uptown Funk AI supplies the street, supporting choreography and camera sequence. Your role is to choose the lead and the generation settings. The reference sound is added to the result, so you do not need to upload a track or write singing instructions. Uptown Funk AI can work as a character introduction or a short group-dance edit. Preview the entire prepared take first, then check the lead after each cut before you share the downloaded video.
Your images define the cast; the reference supplies the movement and scene.
Uptown Funk AI needs one person photo. There are no optional partner or background slots. The complete visible appearance comes from the assigned image.
Uptown Funk AI keeps the reference and sequence ready. There is no motion-video upload, timeline or duration selector on this page. Choose the mode and resolution, then check the displayed length and quote before generating.
The sound from the prepared reference is added to the generated result. Your photo supplies appearance, not a new voice. There is no separate song or dialogue selector; listen to the preview and then check the finished clip with sound.
Use the quote on Generate for your current mode and resolution. General plan examples below may use different models or lengths.
For your first ideas.
$100.0 charged yearly
2,400 credits/year
Up to 400 images
Up to 133 videos
For a steady creative flow.
$360.0 charged yearly
21,600 credits/year
Up to 3,600 images
Up to 1,200 videos
For more creations, more often.
$599.0 charged yearly
48,000 credits/year
Up to 8,000 images
Up to 2,666 videos
Try before you subscribe
Prices in USD; taxes and total shown at checkout. Subscriptions renew automatically; cancel in Billing settings. Subscription credits expire each period; one-time credits never expire.
Refunds: request within 72 hours. Used purchased credits and applicable non-refundable processing costs (up to 6%) are deducted. Terms · Refund Policy
Inputs, roles, settings and the finished video.
Upload one person photo to the labeled slot, select a mode and resolution, and check the quote on Generate. Sign in and submit when ready. Uptown Funk AI supplies the reference and instructions. Your finished video appears in My creations for playback and download.
One: the front lead. The backing group stays with the prepared scene. There are no optional group-member slots, so supplying several people in one photo does not create separately assigned roles.
Yes. Your photo defines the complete lead, including hair, body and visible clothing. Choose the intended outfit in that same picture. The background dancers keep their existing looks, and the tool has no separate clothing-image upload.
This page makes the twelve-second street sequence shown in its preview. It does not produce the full song video, build new locations or let you choose new camera cuts. The fixed performance is prepared before you upload the lead photo.
No supporting-cast selector is included. The current group, positions and choreography belong to the reference. If you need to cast two or more specific people, choose a template with a matching number of named photo slots.
The extra community clip illustrates another interpretation. Generation on this page uses the primary prepared reference shown above the form. The examples are not alternate source buttons; the chosen mode uses the same core street performance.
All three modes use this same short performance with different generation approaches. The output setting is 12 seconds; actual motion timing can vary. Compare the quote on Generate.
The sound from the prepared reference is added to the generated result. Your photo supplies appearance, not a new voice. There is no separate song or dialogue selector; listen to the preview and then check the finished clip with sound.
Generate shows the quote for your mode and resolution. You need an account with sufficient credits; previewing is free. Download your completed Uptown Funk AI video from My creations and add captions in your usual editor if needed.
Bring your chosen photos to the prepared performance and review your quote.
