How the ARLO sneaker unboxing was made with no creator, no shoe and no box: two reference images, a hero frame with the product already in the box, one timed prompt, one video model, all through one connector. The exact prompt is below, ready to paste.
Open Nano Banana Pro (gemini-3-pro-image) and make two stills. One: the product on seamless white, three-quarter side profile so every panel and lace is visible, with the brand marks described in words (for a client, use their real packshot). Two: a phone selfie of the creator in the room where the unboxing happens, written like a casting note: hair, skin, earrings, top. Add the realism layer every time: visible pores, flyaway hairs, no smoothing, subtle sensor noise, muted natural grade. Fictional brands only when you are practising.
02
02Step 2
Put the product in frame one
Make one more image with both references attached and say what each is for: reference 1 is the product, reproduce it exactly; reference 2 is the person and the room, identity only. Describe the opening frame: her at the counter, the open shoebox between her and the lens, one shoe visible under half-folded tissue. This is the start frame of the video. Because the product is already in the frame, the model never has to invent it, which is the single biggest reason unboxings drift. Fix the shoe here, not in the video.
03
03Step 3
Write the prompt as a shot list
Copy the prompt below and change only the product, the person and the four lines. Keep the shape: an identity lock at the top, four timed beats (reveal, first look, try-on, walk), each with one camera position, one action and one line in quotes, then a style line and a negative line. Name the sounds you want (cardboard, tissue, laces). Stay under 300 words.
04
04Step 4
Run it through one connector
In Claude Code, the ElevenLabs connector gives you the image model and the video model behind one login (add it with claude mcp add --transport http elevenlabs https://api.elevenlabs.io/v1/mcp). Wire the hero frame into Kling 3 Pro as the start frame, 15 seconds, 16:9, native audio on, and ask for the estimate first. The 15-second clip is about $3 in credits; every still is about a quarter. Expect the render to take longer than the estimate says.
05
05Step 5
QC like an editor, then post the breakdown
Watch the clip three times: once for the face across the cuts, once for the shoe (same panels, same laces, same sole), once for the hands. If one shot drifts, regenerate the still for that shot and re-run. Then post the breakdown, not just the ad: the clip on top, the two references under it, the prompt scrolling while it plays. That format is the post you are reading this from.
The exact video prompt (copy it, change the product, the person and the four lines)
Create a realistic 15-second UGC unboxing video using the provided woman as the consistent main character and the provided ARLO high-top sneaker as the exact product reference. Keep her face, curly high bun, olive skin, gold hoops and white ribbed tank identical throughout. The sneaker keeps its exact silhouette, sage green and cream leather panels, black collar, black laces and white cupsole. Do not redesign, recolor or alter the shoe.
0:00-0:03 REVEAL. Stationary iPhone on the kitchen counter, facing her. The open shoebox sits on the counter between her and the lens, one sneaker visible under half-folded tissue paper. She peels the tissue back with both hands and leans in. Dialogue: "Wait... look what just showed up." Real cardboard and tissue-paper sounds.
0:03-0:06 FIRST LOOK. Hard cut, same camera. She lifts one sneaker out of the box and holds it toward the lens, turning it so the side profile is clearly visible, eyes moving between the shoe and the camera. Dialogue: "No way. Okay, these are actually so clean."
0:06-0:11 TRY ON. Hard cut to a lower stationary iPhone angle by the counter stool. She sits, slides her foot into the sneaker and pulls the black laces tight with a quick natural tug. Dialogue: "Okay, the fit is unreal."
0:11-0:15 WALK. Hard cut. She stands, taps the toe on the kitchen floor, takes two steps toward the camera and looks down at the shoes, then back up with a small grin. Dialogue: "Yeah. These are staying on all week."
Visual style: iPhone camera quality, natural window daylight, slightly imperfect exposure, real room ambience, visible skin texture, no filters, no studio lighting, not a commercial. Audio: her natural voice, cardboard, tissue and lace sounds. No morphing hands, no extra people, no on-screen text.
Want this running for you?
Build it step by step inside AI Creative OS, with me in the thread.
