Quick answer
Starrd's Bad Sekki: Wing Man template puts you and two friends in the viral wings skit from TikTok creator @dr.hon.bad_sekki. Upload three photos. Photo 1 and photo 2 sit at a long table at an outdoor restaurant at dusk, cracking up over chicken wings while the phone whips back and forth between them. Photo 3 stares from a far table, gets a hard punch-in at 9.8 seconds, walks over and stands over them stone-faced, then breaks and collapses laughing with photo 1, leaving photo 2 ignored with their chin on their hands. The whip-pans, cuts and timing are copied from the original clip as a depth map, and everyone keeps their own face, hair and outfit. Pets work too, sitting up at the table with real paws. The original laughter is on it. 30 seconds, vertical 9:16, Seedance 2.5, 480p, 250 credits (about $12.50).
Two friends can't stop laughing over chicken wings. Across the patio, a third is staring. He gets up, walks over, stands over the table with a stone face, and then he's the one laughing, leaving somebody out. Three photos put you and your friends in the viral Bad Sekki wings skit. Here it is:
Bad Sekki: Wing Man
Three photos. Two of you crack up over wings, the third walks over stone-faced, and somebody ends up ignored. 30 seconds.
What You Get
- Three roles, one table. Two friends laughing over wings and one stranger staring them down.
- The real camera. A phone whipping from face to face across the table, plus the hard punch-in on the stare.
- The turn. The stone-faced walk over, the break at about 18.6 seconds and the two of them collapsing together.
- The payoff. Photo 2, ignored, chin on their hands, deadpan to the end.
- Your own look. Your faces, your hair and the clothes from your photos, at the same outdoor restaurant.
- People or pets. A dog or cat sits up at the table with real paws.
- 30 seconds, vertical 9:16, with the original laughter, ready for TikTok, Reels and Shorts.
What the Video Actually Is
The clip is from Jamaican TikTok creator @dr.hon.bad_sekki, posted on October 16, 2026 (15.9M+ plays, 1.9M+ likes and 500K+ shares so far). It's filmed on a phone at an outdoor restaurant at dusk, with a stage and a huge colourful mural behind the table. There's no song and almost no dialogue: the whole thing runs on laughter, faces and that one long walk across the patio.
Why it suits AI: the joke only works when you know the people. Getting ignored by your actual friends is funnier than watching strangers do it, and two photos of them plus one of you is all it takes. We named this one Wing Man for the chicken wings and the guy who shows up.
The 30 Seconds, Beat by Beat
| Time | What happens |
|---|---|
| 0:00 | Photo 1 at the right of the table, looking down at the food |
| 0.2s | Fast whip-pan left to photo 2, leaning over the table and laughing, photo 3 small and far behind |
| 2.5s | Whip-pan right: photo 1 laughs with a huge open grin |
| 4.6s | Whip-pan left: photo 2 laughs with the head tipped back |
| 6.6s | The camera swings across the patio: photo 3 is alone at the far table, staring |
| 7.6s | Back to photo 1, still laughing |
| 9.8s | Hard cut to a punch-in on photo 3's stunned stare |
| 10.6s | Hard cut back to the wide: photo 2, palms on the table, laughing |
| 12.0s | Photo 3 gets up and walks straight to the table, unsmiling |
| 14.0s | Photo 3 stands over the table, stone-faced, while photo 1 looks up |
| 18.6s | Photo 3 finally breaks into a laugh |
| 20.5s | Photo 1 and photo 3 collapse into each other, laughing as hard as they can |
| 24.5s | The camera pans to photo 2, who gives it one flat look |
| 27.2s | Photo 2's chin rests on their hands, ignored |
| 29.0s | The camera swings back: the other two are digging into the wings |
Your Look, Their Table
- Your own outfits. Everyone wears the clothes from their own photo. If a photo stops at the waist, the rest of the outfit is filled in to match its style.
- The same restaurant. The table of wings and fries, the patio, the stage and the mural stay as they are in the clip.
- Your own hair. The original performers' hairstyles stay out of it, so everyone keeps their own cut and length.
Think about who goes where. Photo 2 is the one who gets ignored, so put the friend who'll find that funniest in the second slot. Clear, well-lit photos where the faces are easy to see work best.
The Fastest Way
Bad Sekki: Wing Man
Three photos: two laughing, one walking over, and somebody ignored. 30 seconds.
Three photos, 250 credits (about $12.50), no prompt. It renders on Seedance 2.5 at 480p, vertical 9:16, 30 seconds, with the original sound 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 the whip-pans, the cuts, everyone's moves and the shape of the place, and drops the faces, the clothes and the colour, so nobody from the original shows up in your video.
2. Make one storyboard sheet of six stills. The two friends laughing, the stare, the stone-faced stand over the table, the collapse and the deadpan, all generated from your three photos, with a depth-map sheet of the original framings as a layout guide.
A photorealistic still from a real vertical phone video, filmed at dusk at an outdoor restaurant with a long black table of chicken wings and fries, a low stage under a silver truss and a huge colourful geometric mural behind. The person from reference image 1 and the person from reference image 3 are collapsed into each other at the right side of the table, arms around each other, the heads together, both laughing as hard as they can with the eyes squeezed shut. Each wears exactly the clothes from their own photo. The rest of the table is empty in the foreground. No text, no logos, no readable signs.
3. Drive it with the depth map. Feed the sheet, your photos 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 sits where: each person's seat, so they're the same person every time the camera whips back.
- The camera: a timed list of every whip-pan and both hard cuts, so the model doesn't invent its own edit.
- The faces: who laughs when, that the starer never smiles before 18.6 seconds, and that the ignored friend never smiles after 24.5.
Put the sound in the depth map so the laughs land, but mute it wherever the person on screen is silent, then lay the full original sound back on top at the end.
Common Mistakes
Driving with the raw clip. The original performers' faces and clothes come straight through. Use the depth map.
Crushing the background to black. A depth map scales to whatever is nearest the lens, so with a table up close the far stage nearly disappears, and the model invents a new one every time the camera moves. Lift the far distances so the stage and truss stay in the map.
Leaving other people's laughter in the driver. When the camera is on the stare, the laughing is coming from off screen. If the model hears it, the starer's mouth starts moving. Mute those stretches in the driver only.
Giving a pet scene panels. Storyboard panels of a pet tend to get copied straight into the film as frozen shots while the camera is meant to be moving. For pets, swap the storyboard for a character sheet: one wide shot of the empty location, then each subject from the front, three-quarter, side and back on a plain background. The depth map then has to carry the framing.
Asking a pet to hold food. Telling a dog to hold a wing turns its paws into fingers. Keep the food on the tray and let its paws rest or wave, empty.
Related Reading
- How to Make the 'Bombaclat Wallahi' AI Video: The Food Truck Meme Starring You: another Caribbean comedy clip, in a single take
- How to Make the 'Push the G*ddamn Button' AI Video: three friends in the Rush Hour standoff
- How to Make the 'I Thought We Were Having a Nice Date' AI Meme: another dinner that goes sideways
- How to Make the 'Every Time Working, No Stopping' AI Video: two friends and one long, deadpan take
- Viral AI Video Trends 2026: every trend we've turned into a template this year
