Gangnam Style AI: make the horse dance video with three friends

Gangnam Style AI takes three photos and puts them into the short version of the horse-riding dance: a night terrace, three performers taking turns, the camera handing the frame from one to the next. The dance, the terrace and the camera work are already filmed — your photos take the faces.

What the Gangnam Style dance is

'Gangnam Style' is PSY's 2012 hit: the signature move raises both arms to mime holding reins, swings one arm across the body and rolls the hips in a gallop, on the 'Oppa gangnam style' chorus. The music video was the first on YouTube to pass a billion views and stayed the most-watched video on the platform for years.

The AI trend is the short, trio version of it. Gangnam Style AI is an independent fan tool with no connection to PSY, YG Entertainment or the platform where the original appeared, and every clip it produces is AI-generated.

The three turns

All three photos are needed for this one — the camera moves from face to face, so a missing photo leaves a hole in the clip.

Each photo takes one turn, so the cast you upload is the cast in the clip — nobody is duplicated and nobody is missing. Write what each person should wear under their own photo, and that instruction applies to that person alone.

How to make a Gangnam Style AI video

1. 1Upload three clear photos — one for each turn.
2. 2Optionally write what each of them should wear.
3. 3Pay once. The render takes five to eight minutes.
4. 4Download the vertical file and post it with the AI label on.

The photos that work

One adult per turn, facing the camera, face sharp and reasonably large in frame, with a plain background behind them. The face is the part that has to survive fifteen seconds of movement — a small or blurred face gets reinvented by the model, and the reinvention drifts.

• One person per photo. Two people in a frame get averaged into a single shape.
• Face clear and lit. Eyes visible if you can manage it.
• Sharp, not mid-movement. Motion blur is the most common cause of a soft head.
• Plain background. Clutter in the source carries into the render.

If you want one person instead of three

This generator is built for a trio. If you only want one face in a short dance clip, the Dime Dime Baby generator on this site takes a single photo and gives you a solo version instead.