Back

Gangnam Style Dance AI: Put Your Face in the Viral Trio Reel

Three friends, one selfie camera, a sunset street in Seoul: the 2026 Gangnam Style trend, where each friend gets a solo to the chorus. Add one photo to take the middle, or bring one or two friends.

The original Gangnam Style AI reel by @mxna.mxnaOriginal reel
  • 1 photo you add
  • 10 to 20 s clip with sound
  • 16:9 like the original clip
  • No watermark

No prompt to write: Add your photo and tap once

Create your own

Ready in up to several minutes · From 126 credits

The Gangnam Style dance trend is back on TikTok in 2026: three friends share one selfie camera and take turns singing the chorus to the lens. The Gangnam Style AI version puts new faces into the biggest reel, filmed in Seoul. From 1, 2 or 3 photos, MakeViral puts you and your friends into it, with the song.

Also called Gangnam Style trio · Gangnam Style in Gangnam · Gangnam Trio · AI Gangnam Style effect · Gamgamstyle · Horse dance · Elevator scene · Gangnam Style Trio Sing

Example

What the Gangnam Style AI video looks like

The people and pets are AI-made, not real persons. The reel versions copy the original clip and come with its original song, which you can turn off; the other versions have original sound. Your result will differ from run to run.

Original reel by @mxna.mxna, 15 s

The original reel by @mxna.mxna (12 October 2026): an AI-made remake of the "gangnam style in gangnam" selfie with three AI-made women at sunset, the first popular AI version of the trend. Solo, Duo and Trio all copy this reel.

Use this reference
The trend's template clip, 20 s

The trend's template clip for the Night trio version: three friends squeeze into a selfie on a city square at night, each gets a solo to the song with a whip pan in between, then all three come back, palms to the lens. Night trio makes these 20 seconds with your three photos.

Use this reference
Original reel by @LOLPETS-b1z, 10 s

The original clip by LOLPETS (20 October 2026): an AI-made orange cat stands up in a kitchen and does the Gangnam Style horse dance, front paws crossed on the reins, a gallop in place and a paw in the air. The Pet version puts your dog or cat into this clip.

Use this reference
Input photo for Gangnam Style AI example (AI-made person)
Input
Result, 10 s, with sound

Made with MakeViral from one photo of an AI-made woman (not a real person): she does the horse dance on a rooftop at sunset, wrists crossed on the reins, a gallop in place and a lasso over her head.

Original reel by @officialpsy, 8 s

The elevator scene of PSY's 2012 "Gangnam Style" music video (official upload, 15 July 2012, over 6.1 billion views): the comedian Noh Hong-chul does the hip thrust dance in a steel elevator while PSY lies on the floor underneath. The Elevator version makes this scene with your two photos.

Step by step

How to make the Gangnam Style AI video on MakeViral

Everything runs in the browser. No editing app, no prompt to write, no watermark.

  1. Add your photo

    Press "Create your own" and add you, face to the camera. Take it with the camera or pick it from your library.

  2. Press Generate

    The button shows the price. Seedance 2.5 puts your photos into the Gangnam Style AI dance trend clip and copies it shot by shot for 15 seconds, with the reel's original song. You write no prompt.

  3. Download or share

    The video is ready in up to several minutes as a 16:9 MP4. Download it, share it from your phone, or find it later in My videos.

Which photo works best?

You need one photo for Solo, two for Duo and three for Trio.

  • Photo 1 is always the friend in the middle, the one who opens and closes the reel. In Duo, photo 2 is the friend on the left. In Trio, photo 2 is on the left and photo 3 on the right.
  • One person per photo, face to the camera, from the chest up or closer. A selfie works well: the reel is a selfie too.
  • Good light on the face. No sunglasses, no mask, no beauty filter, nobody else in the photo.
  • Your clothes and hair come from your photo, not from the women in the reel.
  • Night trio needs three photos in the same order: photo 1 is the singer in the middle, photo 2 the friend on the left, photo 3 the friend on the right. No sunglasses: each face shows in a close solo.
  • Horse dance needs one photo of you: a sharp, well-lit face turned to the camera. A photo from the knees up shows the clothes you dance in.
  • Pet needs one photo of your dog or cat: the whole animal, its face to the camera, one pet per photo, no person in it.
  • Elevator needs two photos: photo 1 is the one who dances, photo 2 the one on the floor, each face to the camera.
  • This template is for adults. Use photos of yourself or of adult friends who agreed. Never a celebrity, a stranger or a child.

Where did the Gangnam Style AI trend start?

"Gangnam Style" is PSY's 2012 K-pop hit. On TikTok it lives on as the gangnam style trio: three friends take turns at one phone camera, singing the chorus, while the others dance behind. A "gangnam style trio" reel from Poland (6 January 2025) has 35.7 million views. In September 2026 the trend came back with friend groups in Poland (16 September, 2.2 million views) and Malaysia (19 September, 3.3 million).

The reel of the 2026 wave is "gangnam style in gangnam" by @emiliyyam: three friends at night in Seoul's Gangnam district (5 October 2026, 17.5 million views). A week later the AI versions began. On 12 October the AI influencer account @mxna.mxna remade it shot for shot with three AI-made women at sunset (106,600 views), the first popular AI version and the reel this page copies. From 19 October @yapayzekaserisi's AI clips of Harry Potter, The Lord of the Rings and Spider-Man characters (his "Gamgamstyle" posts, 601,900 views for the first) made the Gangnam Style AI trend spread, and a one-photo CapCut template of the reel followed. By 22 October 2026, #gangnamstyletrend had 773 videos and #gangnamstyleai 255.

The horse-riding dance of PSY's 2012 music video, the Gangnam Style horse dance, is back in the AI wave too. Its AI pet clips started earlier: an AI-made Labrador dances it in the back of a van in a "Gangnam Style Dog" clip of 30 December 2025 (461,900 views), and an AI-made orange cat does the crossed-paw gallop in a kitchen in a YouTube Short of 20 October 2026. From 21 October 2026 CapCut tutorial captions call the effect the "Gangnam Style horse dance AI video", and AI video sites added the horse dance from one photo, for you or your pet. By 23 October #gangnamstyleai had 566 videos, with about 328 new ones a day.

  1. A "gangnam style trio" reel from Poland, three friends taking turns at one phone camera, starts the format (35.7 million views by October 2026).

  2. An AI-made Labrador dances the Gangnam Style horse dance in the back of a van, an early AI pet version (461,900 views by October 2026). TikTok

  3. The trend is back: a friend group in Malaysia posts its Gangnam Style take (3.3 million views), three days after a four-friend take in Poland (2.2 million).

  4. @emiliyyam and two friends post "gangnam style in gangnam", filmed at night in Seoul's Gangnam district: 17.5 million views and 2.9 million likes by 22 October. TikTok

  5. @mxna.mxna remakes the reel shot for shot with three AI-made women at sunset, the first popular AI version (106,600 views, TikTok AI label). TikTok

  6. @yapayzekaserisi posts "Hogwarts Gamgamstyle Night", AI film characters doing the trio selfie (601,900 views by 22 October); The Lord of the Rings and Spider-Man versions follow on 20 and 21 October. TikTok

  7. LOLPETS posts an AI-made orange cat that does the horse dance on its hind legs in a kitchen, the clip the Pet version copies. YouTube

  8. CapCut template tutorials for the one-photo Gangnam Style AI effect go up in the US, UK and Brazil, and #gangnamstyleaitrend is born; on 22 October #gangnamstyleai has 255 videos.

  9. AI video sites now offer the horse dance from one photo, for you or your pet, and #gangnamstyleai has 566 videos, with about 328 new ones a day.

Copy and paste

The Gangnam Style AI prompts

You do not need these: the one-tap flow runs them for you, together with the trend clip. [Image 1] and [Image 2] are your two photos, and [Video 1] is the trend clip the video copies.

Solo

1 photo: you, face to the cameraSeedance 2.515 s · 720p · 16:9228 credits
Video prompt

Recreate the reference video [Video 1] shot for shot: the same wide handheld selfie video at sunset on a city sidewalk between glass towers, flags on tall poles, cars and a few people passing, the same arm's-length selfie camera, cuts, framing, timing and moves. The ONLY change: the friend in the middle is now the person in [Image 1]. Use [Image 1] as adult Person A at center in [Video 1]. Follow the exact reference sequence: group, center close-up, right solo, left solo, center return. Keep Person A's face, hairstyle, outfit, body proportions and screen position consistent. [Image 1] replaces the woman in the middle with the wavy, shoulder-length dark-brown bob and bangs in the black leather jacket, in EVERY shot: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). They wear the clothes from [Image 1]. NO black leather jacket and no bob with bangs unless [Image 1] shows them. The same real person from the first second to the last, so their friends recognize them at once. Never morph, never drift back to the original woman's face. The friend on the left (black baseball cap, white turtleneck) and the friend on the right (long straight black hair, white lace camisole) stay exactly as in the video, with their own faces, also in their solo shots. Shots, matching the reference second by second: 0-2 s: group selfie, the three side by side, smiling and singing along. 2-4.9 s: the middle friend alone, sings to the lens, points at it, sways. 4.9-8.4 s: the right friend alone by the road, a hair flip and a wave. 8.4-12.3 s: the left friend alone on a side street with orange cones, hands on the head, then a finger heart. 12.3-15 s: the middle friend again, close to the lens, sings and dances. One head per person, on that person's own shoulders. Never a fourth friend; the people passing far behind stay small strangers. No text, no logos, no watermark.

2027 characters

Duo

2 photos: you, in the middle + your friend, on the leftSeedance 2.515 s · 720p · 16:9228 credits
Video prompt

Recreate the reference video [Video 1] shot for shot: the same wide handheld selfie video at sunset on a city sidewalk between glass towers, flags on tall poles, cars and a few people passing, the same arm's-length selfie camera, cuts, framing, timing and moves. The ONLY change: the friend in the middle is now the person in [Image 1], and the friend on the left is now the person in [Image 2]. Use [Image 1] as adult Person A at center, [Image 2] as adult Person B at screen-left, in [Video 1]. Follow the exact reference sequence: group, center close-up, right solo, left solo, center return. Keep each person's face, hairstyle, outfit, body proportions and screen position consistent; do not swap roles or merge identities. Person A: [Image 1] replaces the woman in the middle with the wavy, shoulder-length dark-brown bob and bangs in the black leather jacket, in EVERY shot: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). They wear the clothes from [Image 1]. NO black leather jacket and no bob with bangs unless [Image 1] shows them. Person B: [Image 2] replaces the woman on the left in the black baseball cap and the white turtleneck, in EVERY shot, also in the left solo: copy the exact face from [Image 2] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). They wear the clothes from [Image 2]. NO black cap and no white turtleneck unless [Image 2] shows them. The same real people from the first second to the last, so their friends recognize them at once. Never morph, never drift back to the original women's faces. The friend on the right (long straight black hair, white lace camisole) stays exactly as in the video, with her own face, also in her solo shot. Shots, matching the reference second by second: 0-2 s: group selfie, the three side by side, smiling and singing along. 2-4.9 s: the middle friend alone, sings to the lens, points at it, sways. 4.9-8.4 s: the right friend alone by the road, a hair flip and a wave. 8.4-12.3 s: the left friend alone on a side street with orange cones, hands on the head, then a finger heart. 12.3-15 s: the middle friend again, close to the lens, sings and dances. One head per person, on that person's own shoulders. Never a fourth friend; the people passing far behind stay small strangers. No text, no logos, no watermark.

2562 characters

Trio

3 photos: you, in the middle + friend 2, on the left + friend 3, on the rightSeedance 2.515 s · 720p · 16:9228 credits
Video prompt

Recreate the reference video [Video 1] shot for shot: the same wide handheld selfie video at sunset on a city sidewalk between glass towers, flags on tall poles, cars and a few people passing, the same arm's-length selfie camera, cuts, framing, timing and moves. The ONLY change: the three friends are now the people in [Image 1], [Image 2] and [Image 3]. Use [Image 1] as adult Person A at center, [Image 2] as adult Person B at screen-left, [Image 3] as adult Person C at screen-right, in [Video 1]. Follow the exact reference sequence: group, center close-up, right solo, left solo, center return. Keep each face, hairstyle, outfit and screen position; do not swap roles or merge identities. A: [Image 1] replaces the woman in the middle (dark-brown bob with bangs, black leather jacket) in EVERY shot: the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), the clothes from [Image 1]. NO leather jacket, no bob unless [Image 1] shows them. B: [Image 2] replaces the woman on the left (black cap, white turtleneck) in EVERY shot: the exact face from [Image 2] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), the clothes from [Image 2]. NO cap, no turtleneck unless [Image 2] shows them. C: [Image 3] replaces the woman on the right (long straight black hair, white lace camisole) in EVERY shot: the exact face from [Image 3] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), the clothes from [Image 3]. NO long black hair, no camisole unless [Image 3] shows them. The same real people from the first second to the last, so their friends recognize them at once. Never morph, never drift back to the original women's faces. All three change: no one from the video stays, also in the solos. Shots, matching the reference second by second: 0-2 s: group selfie, the three side by side, smiling and singing along. 2-4.9 s: the middle friend alone, sings to the lens, points at it, sways. 4.9-8.4 s: the right friend alone by the road, a hair flip and a wave. 8.4-12.3 s: the left friend alone on a side street with orange cones, hands on the head, then a finger heart. 12.3-15 s: the middle friend again, close to the lens, sings and dances. One head per person, on that person's own shoulders. Never a fourth friend; the people passing far behind stay small strangers. No text, no logos, no watermark.

2687 characters

Night trio

3 photos: you, the singer in the middle + friend 2, on the left + friend 3, on the rightSeedance 2.520 s · 720p · 16:9304 credits
Video prompt

Recreate the reference video [Video 1] shot for shot. The ONLY change: the three women are now the people in the photos. REFS: [Image 1], [Image 2] and [Image 3] are photos of the three people who appear in the video, one person per photo: [Image 1] = PERSON A, the singer, in the CENTRE; [Image 2] = PERSON B, on the LEFT; [Image 3] = PERSON C, on the RIGHT, each with his or her own face, hair, body and clothes from the photo. Copy their faces, skin, hair, bodies and clothes exactly, the same real face as in the photo in every frame, close and far. [Video 1]: 20 seconds, horizontal 16:9, a handheld night music-video clip: three young women dance and lip-sync to the camera on a city square at night. Shot order: 0-1.5 s all three together in a tight arm's-length selfie, faces filling the frame; 1.5-4.5 s close-up of the centre woman alone, she sings into the lens; whip pan; 4.7-8.1 s the left woman alone dancing by the lamp posts; whip pan; 8.3-11.9 s the right woman alone dancing in front of the stone building; whip pan; 12-16.2 s close-up of the centre woman alone, she pushes her open palm to the lens and sings; 16.2-20 s all three together again in the same tight selfie, palms to the camera. WHO IS WHO: the CENTRE woman of [Video 1] (the singer) = PERSON A from [Image 1]; the LEFT woman of [Video 1] = PERSON B from [Image 2]; the RIGHT woman of [Video 1] = PERSON C from [Image 3]. Everything that is a person in [Video 1] becomes the matching person from the photos: head, face, hair, body, arms, hands, legs, clothes, at the same position, size in frame, pose and timing, copying every dance move, hand gesture, head turn and expression frame by frame, including the whip pans. FACES FIRST: the same real faces as in the photos in every shot; bare open eyes, nothing on the faces; their own clothes from the photos fitting their own bodies and proportions. NO black sunglasses, NO leather jacket, NO olive bomber, NO striped black jacket unless that person's photo shows them. Never morph, never drift back to the original women's faces. LIP-SYNC (strict): PERSON A's mouth copies the [Video 1] singer's mouth exactly, frame by frame: lips and jaw open and close at the same moments, shaping every word; all three faces are alive, smiling and blinking like [Video 1], eyes into the lens. THE PLACE STAYS THE SAME: the night square, the lamp posts, the lights, the fountain, the buildings, the tree, the night street light and the colour grade stay exactly as in [Video 1]; the light on the new people comes from this place. CAMERA AND CUTS (strict): copy the camera and the editing of [Video 1] exactly: the same shots, the same cuts and whip pans at the same moments, the same framing and handheld shake, the same size of the people in frame. No new shots, no extra zoom, no drift. Keep the timing and the full length. No text, no logos, no subtitles. Photorealistic phone-video footage. HARD CHECKS: exactly three people and they are the three from the photos, in the right places; faces identical to the photos in every close shot; their own clothes.

3084 characters

Horse dance

1 photo: you, face clearSeedance 2.510 s · 720p · 9:16126 credits
Video prompt

A vertical 9:16 dance video, photorealistic, a phone on a small tripod at chest height, on a city rooftop at sunset: a wide flat roof with a low glass railing, glass towers and a warm orange sky behind, golden light on the face. One person does the horse-riding dance to the camera with a cool, serious, deadpan face. The dancer is the person in [Image 1], in EVERY frame: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), so their friends recognize them at once. The face stays the same from the first frame to the last, also while they bounce. Never morph. They wear the clothes from [Image 1]. NO sunglasses, no blue tuxedo jacket and no bow tie unless [Image 1] shows them. If [Image 1] shows an animal, the dancer is that animal standing upright on its hind legs, with its own face, fur and markings and the natural body volume of that animal. The dance, beat by beat: 0-2 s: a medium shot from the knees up, the face large and sharp: they stare into the lens and cross the wrists in front of the chest as if holding the reins. 2-5 s: wrists crossed on the reins and a bouncy gallop in place: a skip on one foot, then the other, knees up, the crossed hands bobbing on the beat; the camera eases back so the hop shows from head to feet. 5-7.5 s: one arm swinging a lasso high over the head while the gallop goes on, the other hand still on the reins. 7.5-9 s: a quick side shuffle left and right, two hops each way, the wrists crossed again. 9-10 s: a last gallop facing the camera, then they stop, point at the lens and grin. Audio: a fast K-pop electro house dance beat with a heavy kick, no singing, no words, and a soft tap of shoes on the roof on each hop. Exactly one person. Anatomy: one head, two arms, two legs, hands with five fingers. No other people, no horse. No text, no subtitles, no logos, no watermark.

1980 characters

Elevator

2 photos: you, the one who dances + your friend, on the floorSeedance 2.510 s · 720p · 9:16126 credits
Video prompt

[Image 1] and [Image 2] are the two people. A vertical 9:16 comedy dance video, photorealistic, one continuous take from a camera fixed at chest height in the open doorway of a small steel elevator: brushed steel walls, handrails and a bright ceiling light. The one standing who dances becomes the person in [Image 1]; the one on the floor underneath becomes the person in [Image 2]. The dancer is the person in [Image 1], in EVERY frame: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). The one on the floor is the person in [Image 2], in EVERY frame: copy the exact face from [Image 2] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). Each person wears the clothes from their own image, never a dark jacket or a navy suit and tie unless their image shows them. NO sunglasses unless their image shows them. Both are real, photorealistic people. Never blend their faces, never swap their clothes. Each face stays the same from the first frame to the last, so their friends recognize them at once. If an image shows an animal, that one is that animal with its own face, fur and markings and the natural body volume of that animal: the dancer stands up on its hind legs, the one on the floor lies on its belly. The scene, beat by beat: 0-1.5 s: the elevator doors slide open. The dancer stands in the middle, legs wide, knees bent, arms held out low at the sides, a cool, serious, deadpan face to the lens. The one on the floor lies on the stomach between the dancer's feet, propped on the forearms, chin up, face to the camera. 1.5-5 s: the dancer does the hip thrust dance: quick hip thrusts forward on the beat, the knees bouncing, the arms swinging out and in, the head bobbing, the eyes on the lens. The one on the floor stays below, mouthing the words to the camera with big mouth moves. 5-7.5 s: the one on the floor looks up at the dancer, then back to the lens with a cheeky, smug face, while the hip thrusts go on, faster. 7.5-9 s: the dancer points at the lens with both hands without missing a beat; the one on the floor raises the eyebrows and grins. 9-10 s: the doors slide shut on them. Keep the steel elevator, the handrails and the ceiling light unchanged. Keep both faces clearly lit: the dancer is seen from head to feet, the one on the floor is close to the lens, the face large and sharp. Audio: a fast K-pop electro house dance beat with a heavy kick and a soft elevator ding as the doors open. No singing, no words. No dialogue throughout the entire video. Exactly two people, nobody else. Anatomy: each one head, two arms, two legs, hands with five fingers; the two never merge. No text, no subtitles, no logos, no watermark.

2925 characters

Pet

1 photo: your pet, whole bodySeedance 2.510 s · 720p · 9:16152 credits
Video prompt

Recreate the reference video [Video 1] shot for shot: the same bright modern kitchen with dark wooden cabinets, warm ceiling spotlights and a pale tiled floor, the same fixed camera low in front of the dancer, the same framing, timing and moves, one continuous take with no cuts. The ONLY change: the cat who stands on its hind legs and dances in the middle of the kitchen is now the pet in [Image 1]. The dancer = the pet in [Image 1], in EVERY frame: the same species and breed, head shape, muzzle, eyes, ears, fur colors, fur length and markings as in [Image 1], with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything, so its owner instantly recognizes it from the first second to the last. Never drift back to the cat of the original video: not the coat, not the stripes and not the face of the cat in the video, unless [Image 1] shows them. If [Image 1] shows a dog or another animal, that animal stands upright on its hind legs in the same kitchen and dances the same moves, with its own muzzle, ears, tongue and tail. The horse-riding dance, beat by beat, exactly as in [Video 1], with the same serious, deadpan face: 0-2.5 s: front paws crossed on the reins and a bouncy gallop in place, lifting one hind leg, then the other. 2.5-5 s: both front paws held up in front of the chest, trotting in place on the beat. 5-6.5 s: a quick side shuffle, one front paw swinging out wide, the tail out for balance. 6.5-8 s: back to the middle, front paws crossed on the reins again, the gallop goes on. 8-10 s: a wide stance, one front paw swinging a lasso high over the head, then the last pose facing the camera. Real live-action footage, one continuous take, a clear and stable face, real animal anatomy, the same pet in every frame, the same fur. Anatomy rules: one head only. Two hind legs and two front legs, furry paws covered in the pet's own fur, never human hands or fingers, no extra legs or paws. Exactly one animal, no people. No text, no captions, no logos, no watermark.

2052 characters

How many credits does it cost?

You pay per video in credits, and the create page shows the exact price on the Generate button before you spend anything. The one-tap price covers the video, made in one step from your photos and the trend clip, charged once. Each version has its own price: Solo 228 credits, Duo 228 credits, Trio 228 credits, Night trio 304 credits, Horse dance 126 credits, Elevator 126 credits, Pet 152 credits. The cheaper models are there if you run the prompts by hand in AI Video.

Video modelSettingsCredits
Solo: Seedance 2.5 (this template)15 s, 720p, copies the trend clip, one tap228
Duo: Seedance 2.5 (this template)15 s, 720p, copies the trend clip, one tap228
Trio: Seedance 2.5 (this template)15 s, 720p, copies the trend clip, one tap228
Night trio: Seedance 2.5 (this template)20 s, 720p, copies the trend clip, one tap304
Horse dance: Seedance 2.5 (this template)10 s, 720p, straight from your photos, one tap126
Elevator: Seedance 2.5 (this template)10 s, 720p, straight from your photos, one tap126
Pet: Seedance 2.5 (this template)10 s, 720p, copies the trend clip, one tap152

One-time packs and plans are on the pricing page. A failed video gives its credits back.

What happens in the Gangnam Style AI video, shot by shot?

The Solo, Duo and Trio versions of the Gangnam Style AI dance copy the same 15 seconds of the AI reel, in a wide selfie shot at sunset on a city sidewalk between glass towers, flags on the poles:

SecondsThe shotSoloDuoTrio
0-2Group selfie: the three friends side by side, smiling and singing alongYou in the middleYou and photo 2All three of you
2-5The friend in the middle alone: sings to the lens, points at it, swaysYouYouYou
5-8.4The friend on the right alone by the road: a hair flip and a waveThe reel's friendThe reel's friendPhoto 3
8.4-12.3The friend on the left alone on a side street: hands on the head, a finger heartThe reel's friendPhoto 2Photo 2
12.3-15The friend in the middle again, close to the lens, sings and dancesYouYouYou

The song goes back on after the run, on the same seconds, so the clip is ready to post as a Gangnam Style dance video. Every run is a new take, so results differ.

Solo, Duo or Trio: which version should you pick?

Press "Create your own" and pick one, or press the button under the reel on this page.

Solo (default)DuoTrio
Photos1: you2: you and a friend3: you and two friends
Who changesThe friend in the middleThe middle and the left friendAll three friends
Your solo shots2, plus the group selfie2 for you, 1 for your friend2 for you, 1 for each friend
FrameWide 16:9, 720p, like the originalThe sameThe same
Length15 s15 s15 s
SoundThe song from the reel, put back on after the run; you can turn it offThe sameThe same
TimeUp to several minutesThe sameThe same

Trio is the gangnam style trio as people know it: three friends, one camera, a solo each, the Gangnam Style dance group clip for a night out. Duo is for you and your best friend; the third friend stays as in the reel. Solo needs one photo: you take the middle, the friend who opens and closes the clip, and the two others stay. The videos come from top-quality AI video models, including Seedance 2.5. The exact price shows on the Generate button before you spend anything.

Horse dance and Pet: the Gangnam Style horse dance for you or your pet

The Gangnam Style horse dance is the horse-riding dance of the 2012 music video, and the AI wave brought it back. Two versions do it from one photo:

Horse dancePet
Photo1: you1: your dog or cat
What happensOn a city rooftop at sunset, you cross your wrists on the reins, gallop in place, swing a lasso over your head, shuffle left and right and point at the cameraYour pet stands up in a bright kitchen, crosses its front paws on the reins, gallops in place, shuffles to the side and ends with a paw in the air
How it is madeStraight from your photo, with no reel and no in-between pictureYour pet goes into the AI cat clip by LOLPETS, shot for shot
FrameVertical 9:16, 720pVertical 9:16, 720p
Length10 s10 s
SoundA K-pop dance beat made with the video, not the song: add the Gangnam Style sound when you postThe song from the AI cat clip, put back on after the run; you can turn it off

Horse dance is the horse dance AI for people: a gangnam style horse dance ai clip of you, with your face and your clothes, the deadpan face and every step written out for the AI. Pet turns your dog into a gangnam style dog or your cat into a gangnam style cat: the gangnam style dog dance and the gangnam style cat dance are the same horse dance on four paws, standing up. Your pet does not need to dance: the AI does the moves. Every run is a new take, so the steps and the timing differ a little.

Which sound and hashtags should you post it with?

Solo, Duo, Trio and Pet come with the song from their clip, the same seconds the video is cut to. You can turn it off on the result screen and pick the Gangnam Style sound on TikTok when you post instead. Horse dance comes with a K-pop dance beat made with the video, not the song, so add the Gangnam Style sound when you post. The song is PSY's and belongs to its owners, and MakeViral gives you no rights to it; check the platform's music rules before you use the clip in an ad or a paid post.

Why wide and not vertical? The 2026 reel and every AI version of it are wide 16:9, so Solo, Duo and Trio are too. TikTok and Reels show them with bands above and below, like the original. Horse dance and Pet are vertical.

Hashtags: #gangnamstyle (190,641 videos), #gangnamstyletrend (773 videos and 5.9 million views on 22 October 2026), #gangnamstyleai (255 videos) and the new #gangnamstyleaitrend. Keep the platform's AI label on.

Want more K-pop and friend dances? Try the APT. duo, the A2O LITE NEON dance or the SaWaDiKa dance.

What goes wrong, and how do you fix it?

ProblemFix
A face looks like a woman from the reelUse sharp, well-lit photos with the face turned to the camera, then run it again.
A black leather jacket, a black cap or long black hair shows upThe reel's women wear them. The prompt bans them unless your photo has them; run it again.
A man gets long hair or makeupEach photo keeps its own gender and hair; if a shot slips, run it again.
A face blurs for a moment at about 8 or 12 secondsThe reel whips the camera between the solos there; it lasts a split second.
Two friends swap places (Duo, Trio)Keep the photo order: photo 1 in the middle, photo 2 on the left, photo 3 on the right.
The video model refuses a photoSome photos get refused. The credits come back; try another photo.
FAQ

Gangnam Style AI trend questions

What is the Gangnam Style AI trend?
It is the AI version of the 2026 Gangnam Style trend on TikTok. The real trend is a selfie of three friends who sing the chorus of PSY's 2012 song, each with a solo, made famous by the "gangnam style in gangnam" reel of 5 October 2026 (17.5 million views). The Gangnam Style AI trend puts new faces into that reel: AI-made women, film characters, or your own face from one photo.
What is the gangnam style trio?
It is the TikTok format behind the trend: three friends take turns at one phone camera, singing the chorus while the others dance behind. A "gangnam style trio" reel from January 2025 has 35.7 million views, and the 2026 reel from Seoul gives each friend a solo before the group comes back. On this page, the Trio version puts you and two friends into it, a Gangnam Style dance group video from three photos.
Why is Gangnam Style trending on TikTok again in 2026?
The gangnam style tiktok trend came back in September 2026 with group selfies in Poland and Malaysia (2.2 and 3.3 million views), and the gangnam style trend tiktok wave got its biggest reel from Seoul on 5 October (@emiliyyam, 17.5 million views). Since 12 October AI remakes of it spread, so the gangnam style trend 2026 is both a real dance trend and an AI one. Yes, Gangnam Style is back.
What does "gangnam style in gangnam" mean?
It is the caption of the 2026 reel by @emiliyyam: she and two friends did the Gangnam Style trend in the Gangnam district of Seoul itself, at night under Korean flags. The AI remake this page copies moves the same three shots to a sunset street.
How do I make a Gangnam Style AI video?
Press "Create your own", pick Solo, Duo or Trio, and add 1, 2 or 3 photos; photo 1 is always the friend in the middle. Press Generate; the button shows the price first. You get a 15-second Gangnam Style AI video with the song. That is the whole gangnam style ai tutorial: no editing and no prompt. If you wondered how to make a Gangnam Style AI video without an app full of steps, this is it.
Is there a Gangnam Style CapCut template?
Yes: since 19 October 2026 a one-photo gangnam style capcut template of the reel goes around, and the tutorials call it the AI Gangnam Style effect. In CapCut you copy the template link, open it and add a photo. This page is the same gangnam style ai template idea on the web, with Duo and Trio for your friends too. The gangnam style capcut template trend shows how new the AI wave is.
Is this a Gangnam Style dance generator?
Yes. It works as a gangnam style dance ai generator and a gangnam style dance maker: you add photos, and the AI puts each face into the reel's shots, with the song. The gangnam style dance ai copies the moves and the camera of the reel; it does not invent a new dance.
Do I need to know the Oppa Gangnam Style dance?
No. The 2026 Gangnam Style TikTok dance is a selfie sing-along: the friends sing the "Oppa Gangnam Style" chorus, point at the lens, flip their hair and make a finger heart, and Solo, Duo and Trio do those moves with your face. The horse-riding dance from PSY's 2012 music video is part of the AI wave too, and the Horse dance version does it with your face from one photo. Either way the AI dances, so you never have to learn the oppa gangnam style dance.
What is the Gangnam Style dance called?
The gangnam style dance name most people use is the horse dance: the Gangnam Style horse riding dance from PSY's 2012 music video. You cross your wrists as if holding the reins, gallop in place, swing a lasso over your head and shuffle from side to side. If you search what is the Gangnam Style dance in 2026, you also find the trio selfie on this page, a sing-along with a solo for each friend.
Can my dog or cat do the Gangnam Style dance?
Yes. Pick Pet and add one photo of your dog or cat. Your pet goes into an AI clip of a cat doing the horse dance in a kitchen: it stands up, crosses its front paws, gallops in place and ends with a paw in the air, with the song. A cat doing Gangnam Style or a dog doing Gangnam Style, it is the same 10-second clip; dog gangnam style ai videos and the gangnam style pet clips on TikTok work the same way. Use a photo that shows the whole animal.
Is there a horse dance AI that works from one photo?
Yes, the Horse dance version. It is a gangnam style horse dance ai made straight from one photo of you: on a city rooftop at sunset you gallop in place with your wrists on the reins, swing the lasso, shuffle and point at the camera, in 10 vertical seconds with a K-pop dance beat. The horse dance AI keeps your face and your clothes from the photo.
Can I make the Gangnam Style elevator scene with a friend?
Yes, pick Elevator and add two photos: photo 1 is the one who dances, photo 2 the one on the floor. The gangnam style elevator scene is the PSY elevator scene of the 2012 music video, the one that made the comedian Noh Hong-chul the elevator guy: one man does the hip thrust dance in a steel elevator (a lift, in British English) while the other is on the floor underneath, looking up. In our version you thrust and your friend lies propped on the forearms between your feet, in 10 vertical seconds made straight from your two photos, with a K-pop dance beat, not the song. Add the Gangnam Style sound when you post your elevator dance as a meme or a TikTok trend clip.
What is the Night trio, the Gangnam Style trio trend at night?
It is the night take of the gangnam style trio trend: three friends on a lit city square sing along to the bridge and "Oppan Gangnam Style", each with a solo between whip pans, then the group selfie again. AI apps copy it as the "Gangnam Style Trio Sing" effect, and from 19 October 2026 its bot template tutorials spread, the top one with 3.8 million views. The Night trio version puts you and two friends into that gangnam style trio dance from three photos: 20 seconds, wide 16:9, with the song as a gangnam style sing along. Photo 1 is the singer in the middle.
Can I do the Gangnam Style trend with my friends?
Yes. Pick Duo for you and one friend (photo 1 in the middle, photo 2 on the left) or Trio for three friends (photo 3 on the right). Each friend gets a solo shot, and all of you are in the group selfie. Use photos of adults who agreed.
What is Gamgamstyle?
"Gamgamstyle" is how @yapayzekaserisi spelled the trend on his AI clips of film characters (from 19 October 2026). Those clips use real actors' faces, so MakeViral never copies or shows them. This template uses only your own photos.
Is it a Gangnam Style dance challenge or a meme?
Both. The gangnam style dance challenge is the real trio selfie, and the gangnam style dance meme side is the AI part: film characters, AI influencers and now your own face doing the gangnam style viral dance. Your clip is a Gangnam Style dance video you can post as the trend, marked as AI.
Who are the women in the example?
They are AI-made. The example is the reel by @mxna.mxna, an AI influencer account that remade the trend with three AI-made women, so no real person is in it. Your video replaces one, two or all three of them with the people in your photos.
Which AI models make the video?
Top-quality AI video models, including Seedance 2.5. In Solo, Duo and Trio the AI puts your face into the reel itself, shot for shot, wide 16:9 at 720p, and the reel's song goes back on after the run. Pet does the same with your pet and the AI cat clip, vertical. Horse dance is made straight from your photo, vertical. MakeViral picks the model for each run.
What prompt does the Gangnam Style AI trend use?
No creator shared a prompt: the AI app and CapCut templates are closed. Our prompt starts from a copy-ready trio prompt of an AI template site (each photo as one adult in the middle, on the left or on the right, the reel's exact order of group, close-up and solos), plus our tested words that keep your face. For the horse dance no creator shared a prompt either, so ours writes the moves out beat by beat: wrists crossed on the reins, a gallop in place, a lasso over the head, a side shuffle. You never have to write it.
How long is the video and what format is it?
Solo, Duo and Trio: about 15 seconds, wide 16:9 at 720p, like the original reel. Horse dance and Pet: 10 seconds, vertical 9:16 at 720p. Each is an MP4 file with sound and no watermark.
More trends

Other AI video templates

Make your own Gangnam Style AI video

Add one photo and tap once. No prompt to write. 228 credits.

No watermark. A failed video gives its credits back. Secure checkout by Stripe.