Uptown Funk AI: A retro street-performance scene for one person or a small crew.
Lead a sharply dressed funk routine with your own face, a friend or a three-person crew. The generated setting and original funk-style sound create a new performance scene.
The Uptown Funk AI look turns an ordinary portrait into the lead of a sharply dressed street crew. Retro suits, a confident strut, shoulder pops and a camera-facing pose create the music-video mood; the interest is seeing familiar people carry that attitude. It is a new generated street performance, not a recording of you dancing in the original music video.
Smew offers Solo, Duo and Crew with one, two or three adult photos. Each is a ten-second vertical scene with generated audio. The reference song is not attached as a supplied recording, so choose it separately in a publishing library if that is the version you want to use. The cast choice changes who appears, rather than the length of the scene.
Also called Uptown Groove, Uptown Funk AI crew, retro street dance
Example
See the Uptown Funk AI reference
Credited examples explain the trend’s staging. They are visual references, not Smew customer results; your generated details and movement can differ.
Trend reference
A reference for the scene and timing by @sergirodriguz. This sample is not a Smew customer generation. Compare the framing and sequence rather than expecting a frame-for-frame duplicate. View the credited creator’s post.
Start with the right version and clear photos; the template provides the scene instructions.
Choose the scene and cast
Open Create and choose the version that matches the result you want. Check the photo-slot labels before uploading: one identity belongs in each slot. A reference sample shows the idea; the choices on Create define which people or pets Smew can actually place in that scene.
Add photos and review the output
Upload the requested photos, wait for processing and confirm that the preview shows the correct subject. Compare the selected output, model and credit total. You do not need to record the action or paste a prompt: the template supplies the setting and movement. Submit only when those details match your choice.
Follow the task, then review the finished file
After submission, follow the task on Dashboard while it generates; you can browse templates and see your other tasks there. Once it finishes, open the saved result in Library and inspect the whole clip before downloading. The generated interpretation can vary, especially during fast turns, occlusion and close contact.
Which photo gives this template a fair start?
Use one consenting adult per photo, with the face sharp and looking toward the lens. A knees-up view is useful because the scene includes suits, posture and a full-body strut before moving closer. Avoid sunglasses, a strong profile or a group photo where the model must guess which face belongs to a slot. You do not need a suit in the upload.
For Duo, follow the left and right slot labels. For Crew, photo 1 leads in the center, photo 2 is on the left and photo 3 on the right. Separate portraits are fine; a shared location is unnecessary because the street setting is generated. Similar clarity across the inputs helps all the people remain recognizable during the spin and final pose.
The background of Uptown Funk AI
The 2014 Uptown Funk music video established a recognizable street-crew image: smart suits, relaxed swagger and coordinated movement. AI remakes later used that image with different identities, including tech-CEO reinterpretations discussed in the linked references. Personal-photo versions apply the same joke to a friend group rather than a famous cast.
The collected October examples include guide pages, reposts and @sergirodriguz’s version with cat-headed backup dancers. These explain why people search for Uptown Groove, a CEO dance or an Uptown Funk AI generator. They do not prove that Smew supports celebrity faces or a cat crew. The available choices here use adult portraits in the cast slots, with original generated movement and sound rather than an official artist collaboration.
The original music video is the cultural reference for the suited street-crew image. YouTube
A guide discusses the tech-CEO AI interpretation that introduced the style to another audience. Uptown Funk AI guide
A search-trend link provides discovery context; it is not proof of a unique inventor or fixed popularity level. Google Trends
A repost illustrates the CEO-cast interpretation circulating on TikTok. TikTok
Media.io presents prompt-based interpretations of the street-crew scene, separate from Smew’s choices. media.io
@sergirodriguz’s personal version with cat-headed backup dancers is a credited visual reference. TikTok
Copy and paste
The scene instructions are already included
The built-in recipe sets the setting, roles and sequence. Your photos provide the subjects; you can read the recipe below without needing to paste or rewrite it.
Solo
1 photo: you, face clear (knees up is best)Seedance 2.5 Video Edit15 s · 720p · 9:16126 credits
Video prompt
Edit [Video 1]. Replace only the explicitly mapped source subjects in place:
[Image 1] replaces the center lead dancer; photo slot: You, face clear (knees up is best), in every shot where that subject appears.
[Image 1]: Copy the uploaded person's face, facial structure, eyes, skin tone, age, hair and facial hair or absence of facial hair. Remove source facial hair or hairstyles that the upload does not have. Keep identity consistent across every shot. Keep the source outfit unless the selected variant explicitly changes it or requires a body/species change.
Selected variant: Solo / main. Apply only the requested cast, wardrobe, setting or effect changes for this variant; preserve the source action and shot timing instead of inventing a new scene sequence.
Use the complete preview as the source for the Uptown Funk AI / Solo variant. Preserve its actual action, effect progression, camera moves, shot sequence, physical interactions and mouth/jaw timing. Photo-role labels determine the intended identity assignment; never assign uploaded faces to unrelated background people or props.
Track each source subject through front, profile, back and occluded views. Keep all non-target subjects unchanged. Never duplicate an uploaded identity, merge subjects, swap their roles or transfer an identity to a prop or background subject.
Preserve the complete source video from its first frame to its last: source duration, frame order, every shot boundary, playback speed, camera movement, framing, lighting and original performance; keep background/props unless the selected variant explicitly changes them. Preserve each subject's original head, gaze, body, hand/paw gestures, expression, mouth and jaw opening/closing and their exact source timing. Do not create a new dance, scene, shot list, dialogue or lyrics. Do not add, remove, reorder, shorten, extend or retime shots or actions.
Produce silent video. The matching unmodified original soundtrack is restored separately after this edit. Do not generate speech, singing or music. Do not add new captions, subtitles, logos or a watermark.
2 photos: you (left), face clear + your friend (right), face clearSeedance 2.5 Video Edit15 s · 720p · 9:16126 credits
Video prompt
Edit [Video 1]. Replace only the explicitly mapped source subjects in place:
[Image 1] replaces the center lead dancer; photo slot: You (left), face clear, in every shot where that subject appears.
[Image 2] replaces the separate left supporting dancer; photo slot: Your friend (right), face clear, in every shot where that subject appears.
[Image 1]: Copy the uploaded person's face, facial structure, eyes, skin tone, age, hair and facial hair or absence of facial hair. Remove source facial hair or hairstyles that the upload does not have. Keep identity consistent across every shot. Keep the source outfit unless the selected variant explicitly changes it or requires a body/species change.
[Image 2]: Copy the uploaded person's face, facial structure, eyes, skin tone, age, hair and facial hair or absence of facial hair. Remove source facial hair or hairstyles that the upload does not have. Keep identity consistent across every shot. Keep the source outfit unless the selected variant explicitly changes it or requires a body/species change.
Selected variant: Duo / duo. Apply only the requested cast, wardrobe, setting or effect changes for this variant; preserve the source action and shot timing instead of inventing a new scene sequence.
Use the complete preview as the source for the Uptown Funk AI / Duo variant. Preserve its actual action, effect progression, camera moves, shot sequence, physical interactions and mouth/jaw timing. Photo-role labels determine the intended identity assignment; never assign uploaded faces to unrelated background people or props.
Track each source subject through front, profile, back and occluded views. Keep all non-target subjects unchanged. Never duplicate an uploaded identity, merge subjects, swap their roles or transfer an identity to a prop or background subject.
Preserve the complete source video from its first frame to its last: source duration, frame order, every shot boundary, playback speed, camera movement, framing, lighting and original performance; keep background/props unless the selected variant explicitly changes them. Preserve each subject's original head, gaze, body, hand/paw gestures, expression, mouth and jaw opening/closing and their exact source timing. Do not create a new dance, scene, shot list, dialogue or lyrics. Do not add, remove, reorder, shorten, extend or retime shots or actions.
Produce silent video. The matching unmodified original soundtrack is restored separately after this edit. Do not generate speech, singing or music. Do not add new captions, subtitles, logos or a watermark.
3 photos: you (middle), face clear + friend 2 (left), face clear + friend 3 (right), face clearSeedance 2.5 Video Edit15 s · 720p · 9:16126 credits
Video prompt
Edit [Video 1]. Replace only the explicitly mapped source subjects in place:
[Image 1] replaces the center lead dancer; photo slot: You (middle), face clear, in every shot where that subject appears.
[Image 2] replaces the separate left supporting dancer; photo slot: Friend 2 (left), face clear, in every shot where that subject appears.
[Image 3] replaces the separate right supporting dancer; photo slot: Friend 3 (right), face clear, in every shot where that subject appears.
[Image 1]: Copy the uploaded person's face, facial structure, eyes, skin tone, age, hair and facial hair or absence of facial hair. Remove source facial hair or hairstyles that the upload does not have. Keep identity consistent across every shot. Keep the source outfit unless the selected variant explicitly changes it or requires a body/species change.
[Image 2]: Copy the uploaded person's face, facial structure, eyes, skin tone, age, hair and facial hair or absence of facial hair. Remove source facial hair or hairstyles that the upload does not have. Keep identity consistent across every shot. Keep the source outfit unless the selected variant explicitly changes it or requires a body/species change.
[Image 3]: Copy the uploaded person's face, facial structure, eyes, skin tone, age, hair and facial hair or absence of facial hair. Remove source facial hair or hairstyles that the upload does not have. Keep identity consistent across every shot. Keep the source outfit unless the selected variant explicitly changes it or requires a body/species change.
Selected variant: Crew / crew. Apply only the requested cast, wardrobe, setting or effect changes for this variant; preserve the source action and shot timing instead of inventing a new scene sequence.
Use the complete preview as the source for the Uptown Funk AI / Crew variant. Preserve its actual action, effect progression, camera moves, shot sequence, physical interactions and mouth/jaw timing. Photo-role labels determine the intended identity assignment; never assign uploaded faces to unrelated background people or props.
Track each source subject through front, profile, back and occluded views. Keep all non-target subjects unchanged. Never duplicate an uploaded identity, merge subjects, swap their roles or transfer an identity to a prop or background subject.
Preserve the complete source video from its first frame to its last: source duration, frame order, every shot boundary, playback speed, camera movement, framing, lighting and original performance; keep background/props unless the selected variant explicitly changes them. Preserve each subject's original head, gaze, body, hand/paw gestures, expression, mouth and jaw opening/closing and their exact source timing. Do not create a new dance, scene, shot list, dialogue or lyrics. Do not add, remove, reorder, shorten, extend or retime shots or actions.
Produce silent video. The matching unmodified original soundtrack is restored separately after this edit. Do not generate speech, singing or music. Do not add new captions, subtitles, logos or a watermark.
You pay in credits. The Generate button shows this price before you spend anything. These are the options on this page.
Option
Model
What you get
Credits
Solo
Seedance 2.5 Video Edit
15 s · 720p · 9:16
126
Duo
Seedance 2.5 Video Edit
15 s · 720p · 9:16
126
Crew
Seedance 2.5 Video Edit
15 s · 720p · 9:16
126
One-time packs and plans are on the pricing page. A failed video gives its credits back.
A short street-crew performance, rather than a full song
The intended action begins with the cast facing the camera, then taking a few confident steps with shoulder movement. Side steps, small snaps and a playful head gesture keep the dance readable before a spin, a raised-hand freeze and a final lapel-adjusting pose. The sunny street, brick façades and retro tailoring supply a music-video setting without requiring a filmed location.
This is a ten-second interpretation of the style, not the official choreography or a reconstruction of an entire song. Check whether the lead remains distinct from the backup dancers, especially as bodies overlap or the camera moves closer. A convincing suit and street are not enough if the faces blend during the main action.
Pick one lead, a pair or three friends
Solo gives one uploaded person the lead, with generated backup dancers. Duo puts two uploaded adults at the front. Crew uses three uploads for the featured group, with photo 1 in the center and the others on the labeled sides. Choose the cast according to who needs to be recognized, rather than adding several faces to one image.
All three current choices use the same duration and credit amount. The difference is identity coverage. A cat-headed backup crew in a reference example is background context, not a supported cat variant in this template. Likewise, the tech-CEO posts explain the meme but are not an invitation to upload public figures. The table lists the actual Smew choices.
The current Smew options are listed below. The photo count belongs to the selected version: an extra person in a single upload is not a substitute for an additional photo slot. The model name describes how the output is made; it does not promise identical faces or motion on every run. Review the selected option and credit total on Create before submitting.
Choice
Photos
Model
Output
Credits
Solo
1
Seedance 2.5
10 seconds, 9:16, 720p
126
Duo
2
Seedance 2.5
10 seconds, 9:16, 720p
126
Crew
3
Seedance 2.5
10 seconds, 9:16, 720p
126
Sound: these choices produce sound generated with the scene, rather than a promised copy of a social-platform recording. Sound heard in a credited reference is not automatically included in every Smew option. If you add platform music later, choose it from that platform’s available library and check the intended use; generating a video does not transfer music rights.
Faces, spins and accidental background detail
A spin can briefly blur the face, but the identity should be readable again when the cast settles into the final pose. If a backup dancer inherits the lead’s face, or two friends merge, check that each source image contains one clear person. A distant group photo is particularly weak for assigning several independent identities.
The model also redraws hands, suits and street signs. Unexpected letters or logos are artifacts rather than a promised design feature. Review the whole take, including the overlap between people, before publishing. A clearer input may help identity, but it cannot guarantee identical choreography, a particular suit shade or flawless text-free backgrounds on every run.
Music and a caption that leaves room for the dance
The clip has generated scene audio rather than a supplied copy of the Uptown Funk recording. If your intended post needs that specific song, select an available licensed platform sound and check the finished timing and mix. Do not assume an AI export grants rights to use a recording in an advertisement.
Let the group’s attitude be the joke. A brief caption about the friends arriving for a night out is enough; long text across the center can hide the spin and poses. Use relevant tags such as the trend name and AI dance if they describe the post. Keep the platform AI label, and avoid presenting the result as an actual music-video appearance or artist endorsement.
FAQ
Uptown Funk AI — questions before you create
What is the Uptown Funk AI trend?+
It is a generated street-crew dance with retro suits, confident walking and playful camera-facing moves. The visual reference comes from the familiar music-video style, with different identities cast as the crew. Smew makes a new ten-second scene from one to three adult photos rather than placing you in an official video.
What was the tech CEO Uptown Funk video?+
AI creators used recognizable tech-CEO identities in an Uptown Funk-style crew, and guides and reposts discussed those clips. That is part of the trend’s background, not a Smew cast option. Use your own adult photo or a consenting adult friend instead of treating a public repost as permission to copy someone’s face.
How do I make the Uptown Funk AI video?+
Open Create, pick Solo, Duo or Crew and fill the labeled photo slots. Check the model, output and credit total, then submit. The template already includes the dance setting and movements. Follow the task on Dashboard and review the saved video in Library; no performance footage is required.
Is this made by or with Bruno Mars or Mark Ronson?+
No affiliation or endorsement is implied. The artist and song names identify the cultural reference people use to find the style. Your generated scene uses the uploaded identities and an original interpretation of the street-crew mood, rather than an official collaboration or authentic music-video appearance.
Does the video have the Uptown Funk song?+
It includes generated scene audio, not a supplied copy of the Uptown Funk recording. If you want that song, choose an available platform sound when publishing and check the relevant use rules. The presence of an artist name in a trend title does not grant recording rights.
Is there a prompt for the Uptown Funk AI trend?+
No. The recipe already describes the strut, small side steps, shoulder movement and final pose. Prompt guides are part of the trend’s reference history, but you do not need to paste one here. Your input decisions are the cast, clear photos and the offered output choice.
Is this an Uptown Funk AI video generator?+
Yes, as a prepared photo-to-video template. It makes the specific street-crew scene offered here, rather than an unrestricted music-video editor or any routine requested by name. The selected cast controls the supplied identities, while the model interprets the choreography, clothing and camera movement.
Can I make an AI group dance video with my friends?+
Duo takes two separate adult photos and Crew takes three. For Crew, put the center lead first, then the left and right identities in their labeled slots. Use one person per upload. A group photo does not reliably substitute for the independent face references requested by the template.
Are the Uptown Funk dance moves the real choreography?+
No exact official choreography is promised. The scene uses broad street-dance cues such as a strut, shoulder pops, a spin and a strong final pose. It is a short generated interpretation of the mood. If you want to learn a real routine, use a dance tutorial rather than the generated motion as instruction.
What is the Uptown Funk meme with cats?+
The credited example includes AI cat-headed dancers, which is one creator’s interpretation. Smew’s current Solo, Duo and Crew options use adult portrait slots and do not list a cat crew or pet variant. The reference explains the trend; it does not add extra supported cast choices.
How long is the video and what format is it?+
All three choices currently produce ten-second, vertical 9:16, 720p videos using Seedance 2.5 at 126 credits. The sound is generated with the scene. Check the selected total on Create before submitting, and compare the cast slots carefully if you are choosing between Duo and Crew.
Is the video real?+
No. It is generated from still photos, with an invented street performance. The people did not need to dance together or visit that location. Use consenting adults and retain the publishing platform’s AI disclosure so viewers understand the result as a playful remake rather than documentary footage.
