Quick answer
Upload one photo to Starrd's Camden Bop template and it puts you doing the Camden Bop — in the real room from your photo, not a stock set. It costs 100 credits (about $5), takes a single photo, works on a person or a pet, and comes out vertical 9:16 at 15 seconds with the real sound underneath.
The same dance, any subject — tap one to make it with your photo.
One photo in, and out comes you doing the Camden Bop in your own hallway — same walls, same floor, same light, one locked vertical shot. Here's exactly what you get:
Camden Bop
One photo, wherever you are. You or your pet, running the bop — real room, real sound. No prompt to write.
Where the Camden Bop Actually Comes From
This one has a real address, and the people who made it are still around to be credited.
The Camden Bop was built by five students out of Camden High School in Camden, New Jersey, who go by the Camden Bop Originators: Ethan Tarte, Myles Thompson, Nafi Muhammad, Rodney Barge Jr. and Haleem Muhammad. Tarte came up with the core move at 16 — he was imagining what it would look like to circle the rink at Camden's Millennium Skate World, and worked it out barefoot in front of his mirror before the rest of the foundation came together.
Their classmates called it corny first. Then it caught on at Camden High, then it left the city entirely, and by mid-2026 it had over a million fans worldwide.
What the dance actually is: hips shifting side to side, arms and heels bouncing against the drum kicks and vocal samples, with heel-toe slides, leg extensions and quick pivots carried over from Jersey Club. That skating-rink origin is still visible in it — the whole thing glides more than it stomps.
Give the Originators Their Credit
Worth saying plainly, because the people who made this asked for it directly.
Philly rapper 2Rare put out a single called Camden Bop and went looking for the Originators specifically so the dance would be attributed to them, putting the crew in the video — which premiered May 7 and has since passed 2.8 million YouTube views. His reasoning, in his own words: "I know how quickly people can steal a wave, and nobody will ever know who the dance was from."
That is the correct instinct and it applies to your video too. If you post one of these, name the dance and name Camden. It costs you a line of caption and it is the difference between participating in something and quietly lifting it.
The dance and the single are not the same thing, and this trips people up when they search. A lot of the viral clips run a different sound than 2Rare's record. Search "camden bop" as a dance, not as a song title, and you'll find the routine rather than the release.
The Fastest Way
Camden Bop
One photo. You doing the Camden Bop in your own room. 15 seconds, vertical, real sound.
Upload one photo. You get back a 15-second vertical clip with the sound on it. No prompt, no CapCut, no learning the routine first.
Why It Uses Your Room, Not a Set
Most templates put you somewhere: a booth, a red carpet, a stadium. This one does the opposite — it reads the background of your photo and rebuilds that room to dance in.
It matters more than it sounds. The Camden Bop spread as hallway footage and bedroom footage and driveway footage. Somebody's actual house, filmed on a phone held by somebody's actual friend. Staging it on an obviously fake set reads as a filter; the same routine in a hallway with a light switch in the wrong place reads as a video someone actually made.
Three rules it follows:
- Your room, not a nicer version of it. It won't tidy up, restyle or upgrade what's behind you. A cluttered kitchen stays a cluttered kitchen.
- No usable background, and only then a fallback. A blank studio wall or a tight head crop has nothing to rebuild, so it uses a plain living room instead of stranding you in a grey void. A bedroom with a bed and a lamp counts as usable — it will use that.
- One subject, alone in frame. It never adds a partner, a crowd or a bystander to fill the space.
So the photo you upload decides the location. Choose accordingly.
It Works on Pets, and Here's the Part That Matters
Dogs and cats do very well on this one, and there's a specific reason.
The failure mode for an animal on a dance template is that the model invents a smaller, animal-appropriate version of every move — a tail wag where the routine has a whole arm, a head tilt where there's a pivot. You end up with a pet that is technically animated and visibly not doing the dance.
The fix is anatomical, not stylistic: the pet gets staged standing upright on its hind legs, and its front legs are treated as arms that have to make the same movements the dancer's arms make, at the same height. Not a paw-dab. The actual gesture.
Measured on our side, that one change nearly doubled how closely the pet's movement tracked the source routine. It's also what keeps the clip from breaking down — when an animal render goes wrong, what happens is the pet vanishes for a few seconds and the original dancer surfaces in its place, and giving the model an explicit way to map an animal body onto human choreography is what prevents that.
Build It Yourself
If you'd rather assemble it by hand, here's the shape of it.
1. Build the still first, with the room already in it. Don't animate your raw selfie. Generate one still of the subject standing full-body in the room, then animate that:
A photorealistic VERTICAL 9:16 photograph of the single subject from the reference photo standing in a real room.THE SUBJECT: standing TALL and FULLY UPRIGHT, body vertical, balanced and stable, NOT sitting, NOT crouching, NOT leaning on furniture. FULL BODY, head to feet, both feet flat on the floor, facing the camera. Arms hang loose and clearly separated from the torso so the whole silhouette reads cleanly. IF THE SUBJECT IS AN ANIMAL IT STANDS ON BOTH HIND LEGS in a confident, balanced, human-like posture, front legs and paws hanging loose like arms — never on all fours, never sitting.PRESERVE the exact identity of the subject — face, hair, skin tone, build, markings and the clothing they are actually wearing. Only the pose and the distance from the camera change.SETTING — USE THE REAL PLACE FROM THE REFERENCE PHOTO. Look at what is BEHIND the subject and rebuild that same real place: the same wall colour, flooring, furniture, doorways, light fixtures and decor, with the light coming from the same direction. Extend it naturally to give clear floor to dance on. Keep it recognisably THEIR place — do not tidy it, redecorate it or swap it for a nicer version.Photorealistic, sharp focus, natural colors. Vertical 9:16. Exactly ONE subject. No text, no captions, no logos, no watermarks, no other people or animals.
2. Drive it with the routine itself. Take that still into a video model that accepts both an image reference and a video reference, and hand it a clip of the dance you want copied. Every step and every arm movement comes from the driving clip — not from your prompt.
3. Say which source wins what. This is the one that separates a good result from mush. The still owns who and where — identity, clothing, the room. The driving clip owns how the body moves. Write that down explicitly, because when the two disagree the model needs a rule rather than an average.
4. Ask for the face, by part, not by feeling. A copied body over a dead face is uncannier than no video at all. Say that the eyes, eyebrows, mouth and jaw follow the driving clip moment for moment — and name no particular expression. Write smiling and you'll get one frozen smile held for fifteen seconds, which is the same deadpan problem arrived at from the other side.
5. Do not describe the moves. The counterintuitive one. Writing bopping on the beat or sliding side to side makes the output worse — the model satisfies your description with the smallest possible version of it and discards the real choreography.
Same goes for framing. Adding "full body", "feet on the floor" or "static locked-off camera" to the video prompt measurably suppresses the movement. Put that language in the still prompt, where it belongs, and keep the video prompt about nothing but the performance.
6. Put the real sound on afterward. Render silent and lay the track over the top. Generated audio over a sound this recognisable is instantly obvious — and asking a model to synthesise audio over a copyrighted reference clip tends to fail moderation anyway. Make sure the track outlasts the video, or the clip gets cut short where the audio stops.
Common Mistakes
A tight head crop. Nothing behind your face means nothing to rebuild, and you get the fallback room instead of your house. If you want your hallway in it, stand in your hallway.
Describing the choreography. Covered above, and it's the single biggest quality killer on dance templates.
Naming an emotion instead of the facial parts. "Make him look confident" gets you one held expression. Point the eyes and mouth at the driving clip and let the routine supply the rest.
Letting a pet stay on all fours. It'll bounce, it won't dance. Stand it up and treat the front paws as arms.
Letting the model generate the audio. Everyone knows this sound. A near-miss is worse than silence.
Posting it with no credit. Name the dance and name Camden. The people who built it asked.
FAQ
What is the Camden Bop? A gliding, bouncy solo dance out of Camden, New Jersey, with heel-toe slides, leg extensions and quick pivots borrowed from Jersey Club.
Who created it? The Camden Bop Originators — Ethan Tarte, Myles Thompson, Nafi Muhammad, Rodney Barge Jr. and Haleem Muhammad, out of Camden High School. Tarte built the core move at 16 from imagining a skating rink.
Is it the 2Rare song? Related, not identical. The dance came first; 2Rare's single put the Originators in the video. Many viral clips use a different sound.
How many photos? One. It's a solo routine.
Does it work on my dog? Yes — standing upright on the hind legs, front paws as arms.
Does it use my room? Yes. It rebuilds the background from your photo, and only falls back to a set room if there's nothing usable behind you.
How much? 100 credits, about $5. Credits never expire.
