Quick answer
Starrd's Put A Mind Chip template recreates the viral 'put a mind chip' dinner interview from two photos. Photo 1 is the guest, the one who calmly explains that when they get married they'll inject "like chips inside of her, so we see each other 24/7", because "she always sees what I see, and I always see what she sees." Photo 2 is the interviewer, who asks "So you would do that? Put a mind chip?" and gets a grinning "Hell yeah." The full 27-second clip is rebuilt shot for shot, all 12 shots at a dinner table in a warm, wood-panelled restaurant, with both people lip-syncing the original audio and keeping their own look. Vertical 9:16, Seedance 2.5, 250 credits (about $12.50).
Two photos in, and out comes you and a friend recreating the viral "put a mind chip" dinner interview: one of you calmly explains the plan to chip your future spouse so you always see what they see, the other asks the only reasonable follow-up. All 12 shots, every line lip-synced. Here it is:
Put A Mind Chip
Two photos. One of you has a plan for married life, the other asks: put a mind chip? The full 27-second interview, lip-synced.
What You Get
- The whole interview. All 27 seconds and all 12 shots, cut at the same moments as the original.
- Two people, two roles. Photo 1 is the guest, photo 2 is the interviewer, and nobody ever swaps.
- Real lip sync. Both of you mouth your own lines to the original audio, and the listener keeps a still, straight face while the other one talks off-screen.
- The performances. The guest's eyes drifting up while he hunts for the words, the slow nods, the small knowing smile and the final grin; the interviewer's hand on the chin and polite, baffled questions.
- The original camera. Medium close-ups over the wine glasses, tight close-ups, the interviewer's wide shot behind the salad, and the push-in on "So you would do that?"
- 27 seconds, vertical 9:16, ready for TikTok, Reels and Shorts.
What the Meme Actually Is
The clip was posted by @lyricalemonade on September 19, 2026, captioned "lazer dim on getting married 🧠", and passed 537,000 plays, 50,000 likes and 9,000 shares. It's a sit-down interview over dinner: a calm interviewer with his hand on his chin, and a guest who lays out his plan for married life as if it's the most romantic, sensible thing in the world.
The joke is how reasonable he sounds. He stumbles for the words ("I'mma put like… I'mma… um…"), lands on "inject", explains it's "so we see each other 24/7", corrects the interviewer's tracking theory ("No, so she always sees what I see"), and then, asked to say it plainly, doesn't flinch.
Why it suits AI: the humour is all timing and faces. Two photos let you and a friend play it completely straight, without memorising a script or booking a restaurant.
The Script, Beat by Beat
| Time | Who | Line |
|---|---|---|
| 0:00 | Guest | "When I get married…" |
| 2.4s | Guest, eyes drifting up | "I'mma put like… I'mma… um…" |
| 6.5s | Guest, tight close-up | "I'mma inject…" |
| 8.9s | Guest | "…make my [explicit] gon' sign a paper, to inject, to inject like chips inside of her." |
| 11.5s | Guest | "So we see each other 24/7." |
| 16.1s | Interviewer, hand on chin | "So you always know where she's at?" |
| 17.5s | Interviewer, off-screen | "But then she knows where you are?" |
| 18.5s | Guest | "No, so she always sees what I see, and I always see what she sees." |
| 22s | Interviewer, camera pushing in | "So you would do that?" |
| 24.3s | Interviewer | "Put a mind chip?" |
| 25.6s | Guest, grinning | "Hell yeah." |
Who plays who: photo 1 is the guest, photo 2 is the interviewer. Put the friend who can keep a straight face while saying something unhinged first.
Your Look, Their Restaurant
- Your own face, hair and clothes. Nobody gets the original's locs, chains or hoodie.
- Your own glasses. If your photo has sunglasses, you keep them on; if it doesn't, you don't get any.
- Their table. Both of you sit at a dinner table in a warm, wood-panelled restaurant, with framed photos on the walls, red wine and a bowl of salad.
Use clear, well-lit face photos where you're looking roughly at the camera. Most of the 27 seconds are close-ups, so your face carries the whole video. If you and your friend are dressed alike, that's fine: the template tells the two of you apart by hairstyle as well as clothes.
The Fastest Way
Put A Mind Chip
Two photos, the full 27-second dinner interview with the original audio, every line lip-synced.
Two photos, 250 credits (about $12.50), no prompt. It renders on Seedance 2.5 at 480p, vertical 9:16.
Build It Yourself
1. Turn the clip into a depth map, one shot at a time. Run the clip through a depth-estimation model (Depth Anything V2 works) and set the contrast per shot: the tight close-ups and the interviewer's wide shot have very different depth ranges.
2. Scrub everything that belongs to the original people. The burned-in yellow subtitles leave letter shapes in the depth map, so mask them in each source frame and inpaint them out of the depth frame. Then clean the shapes that would leak onto your cast: smooth the hair down to a plain, slightly smaller dome so the guest's locs and the interviewer's curls don't come back as your hair, and blur away the interviewer's glasses and the guest's chains. Use a segmentation model (CLIPSeg works) to find hair, eyeglasses and necklaces in every frame.
3. Make one storyboard sheet with a panel per camera setup. Twelve shots boil down to six setups: the guest's medium close-up over the wine glasses, the interviewer's three-quarter close-up with a hand on the chin, the guest's tight close-up, the interviewer's wide shot behind the salad, the guest's medium shot, and the guest's extreme close-up grin. Generate them all from the two photos in one restaurant.
A medium-wide shot of the person from reference image 2 alone at a restaurant table: seated, framed from the waist up, one elbow on the table and one hand at the chin, a white bowl of salad on the white tablecloth in the bottom foreground, honey-brown wood panels, framed black-and-white photos and shelves of wine bottles behind, turned toward the right edge of the frame, listening quietly, mouth closed. Warm amber light, shallow depth of field. No text.
4. Drive it with the depth map and the dialogue. Put the original audio inside the depth video, but mute it wherever the speaker is off-screen (the guest's voice over the interviewer's wide shot, the interviewer's question over the guest's listening shot), so the person on screen doesn't mouth someone else's words. Feed the sheet, both photos and the depth video to a model that copies motion from a reference video (we recommend Seedance 2.5). Then write three things it can't get from a depth map:
- A timed shot list: who is on screen, the framing and the line for each of the 12 shots.
- The speaking windows: exactly when each person's mouth moves.
- The faces: the guest's calm conviction, wandering eyes and final grin; the interviewer's hand on the chin and quiet disbelief.
Lay the full original audio back on at the end.
Common Mistakes
Giving "Put a mind chip?" to the guest. The captions make it look like his line, but it's the interviewer's follow-up question. The guest's answer is "Hell yeah."
Dropping the interviewer's split-second cut-in. In the original he's on screen for about a third of a second while he asks "Put a mind chip?" Models skip shots that short, so slow that shot down to about three quarters of a second instead.
Leaving the glasses in the depth map. The interviewer's frames come through as clear outlines, and your interviewer gets glasses they never wore.
Leaving the off-screen voice in the driver. Whoever is on screen will mouth along to the other person's lines.
Driving with the raw clip. The locs, chains, hoodie and captions come straight through. Use the depth map.
Facing the lens. The original is a two-camera interview: both people look just past the camera at each other. Say so, or they talk to the viewer.
FAQ
How many photos? Exactly two: the guest and the interviewer.
Is it the full clip? Yes, all 12 shots, 27 seconds.
How long is it? 27 seconds, vertical 9:16.
What does it cost? 250 credits, about $12.50.
Related Reading
- How to Make the 'Like 700 MPH' AI Interview Meme: the other deadpan sit-down interview, starring you and a friend
- How to Make the 'I Thought We Were Having a Nice Date' AI Video: another two-person scene at a restaurant table
- How to Make the 'Deep Down In My Heart' AI Video: the crying-interview meme, lip-synced
- Viral AI Video Trends 2026: every trend we've turned into a template this year
