Quick answer
Starrd's Lonyo! template puts you at the centre of the viral 'Lonyo!' crowd dance. Upload one photo and you lead a big crew of dancers in crisp white shirts and black bottoms on a sunlit outdoor court, filmed from high above, across four shots: a high-angle medium shot in the middle of the crowd, an overhead wide of the whole crew moving in unison, a whip-pan to just you and two backup dancers on an open stretch of court, and a whip-pan back to the packed formation. The shots, the cuts and every move are copied from the original clip as a depth map, so they land at the same moments, and you keep your own face, hair and outfit. Pets work too, dancing upright on their hind legs. The song is on it. 25 seconds, vertical 9:16, Seedance 2.5, 480p, 250 credits (about $12.50).
The same dance, any subject — tap one to make it with your photo.
A whole crew dancing in rows on a sunlit court, filmed from high above, and you are the one at the centre leading it. One photo puts you in the viral Lonyo dance. Here it is:
Lonyo!
One photo. You lead the Lonyo dance at the centre of a huge crew on a sunlit court, filmed from above. 25 seconds.
What You Get
- You, front and centre. You're the lead dancer in every shot, at the middle of the formation, grinning and glancing up at the camera.
- A huge crew. Dozens of dancers in crisp white shirts and black trousers or skirts, some with small backpacks, all doing the routine with you.
- Four shots, two whip-pans. A high-angle medium shot in the crowd, an overhead wide of the whole crew, a whip-pan to just you and two backup dancers, and a whip-pan back to the packed formation.
- Your own look. Your face, hair and the clothes from your photo. You're the only one not in white.
- People or pets. A dog or cat leads the crew upright on its hind legs.
- 25 seconds, vertical 9:16, with the song, ready for TikTok, Reels and Shorts.
What the Video Actually Is
The clip is from TikTok creator @downey.ai. It's a dance to "Lonyo!": one person in a green shirt leads a big crew of students in white school uniforms on a sunlit court, and the camera watches it all from high above. Partway through, it cuts hard to a stretch of empty court with only three dancers, then back to the whole crowd. It began showing up as an AI trend at the end of October 2026.
Why it suits AI: the whole point is one person leading dozens, filmed from a drone. You can't round up a school's worth of dancers in matching shirts and book a drone for a 25-second clip. One photo can.
The 25 Seconds, Shot by Shot
| Time | What happens |
|---|---|
| 0:00 | High-angle medium shot: you at the centre of the crowd, knees up in frame, elbows out, grinning |
| 3.5s | Hard cut to the overhead wide: the whole crew fills the court in loose rows, all in unison, you at the centre |
| 10.5s | A fast, blurred whip-pan across the empty court |
| 10.9s | Just three dancers: you in front, two of the crew behind you left and right, long shadows beside you |
| 17.9s | A second whip-pan |
| 18.3s | The packed formation, white court lines across the top of the frame, everyone tight around you to the last frame |
Your Look, Their Crew
- Your own outfit. A hoodie, a suit, a dress: whatever is in your photo leads the crew. You don't get the original's green shirt, and you never get the crew's white shirt unless you're wearing one in your photo.
- Seen head to toe. The overhead shots show your whole figure, so if your photo stops at the waist, the rest of the outfit is filled in to match its style.
A clear, well-lit photo where your face is easy to see works best, and a full-length one keeps your shoes and trousers exactly yours. For a pet, use a photo where its face and coat are clear: it stays a real dog or cat, just upright and dancing.
The Fastest Way
Lonyo!
One photo, and you lead the whole crew in the Lonyo dance. 25 seconds.
One photo, 250 credits (about $12.50), no prompt. It renders on Seedance 2.5 at 480p, vertical 9:16, 25 seconds, with the song on top.
Build It Yourself
1. Turn the clip into a depth map. Run the clip through a depth-estimation model (Depth Anything V2 works). The depth map keeps every dancer's moves, the camera, the cuts and both whip-pans, and drops the faces, the uniforms and the colour, so nobody from the original shows up in your video.
2. Make one storyboard sheet of six stills. The medium shot in the crowd, two overhead wides of the whole crew, two shots of the three dancers, and the final packed formation, all generated from your photo, with a depth-map sheet of the original framings as a layout guide.
A photorealistic still from a music video shot by a drone high above a big sunlit outdoor court: flat pale grey-beige asphalt, thin white painted lines, a low late-afternoon sun throwing long crisp shadows. Dozens of dancers in crisp white short-sleeved shirts with black trousers or black pleated skirts fill the frame in loose rows, all mid-step in unison with their arms swinging out to one side. At the centre of the formation, small in frame, the person from reference image 1 dances the same move, wearing exactly the clothes from their photo. No text, no logos.
3. Drive it with the depth map. Feed the sheet, your photo and the depth video to a model that copies motion from a reference video (we recommend Seedance 2.5). Then write what it can't read from a depth map:
- Who leads: the person at the centre of the formation, in every shot, including the three-dancer shot.
- The cuts: a timed shot list with the hard cut at 3.5 seconds and both whip-pans, so the model doesn't invent its own edit.
- The faces: grinning and confident, glancing up at the camera, mouths closed or smiling.
Lay the song back on top at the end: the depth map carries no sound.
Common Mistakes
Driving with the raw clip. The original dancer's face and green shirt come straight through. Use the depth map.
Not saying the lead stands out. If you only describe the crew's white shirts, the model dresses you in one too. Say plainly that the lead wears their own clothes and the crew are the only ones in white.
Copies of you in the crowd. With dozens of faces to fill, the model reuses yours. Say the crew are anonymous dancers and that none of them has the lead's face.
Related Reading
- How to Make the Car Alarm Dance AI Video: another dance copied move for move, starring your pet
- How to Make the ATEEZ BAD AI Dance Video: lead a dance with two friends behind you
- How to Make the Toosie Slide AI Video: Drake's dance from one photo
- How to Make the Stadium Calm Down AI Video: you, in front of a few thousand people
- Viral AI Video Trends 2026: every trend we've turned into a template this year
