Wipes: first-last is sealed tub to flipped lid
Two stills you own. Interpolate. Do not invent a new scent badge mid-clip.
Two stills you own. Interpolate. Do not invent a new scent badge mid-clip.
A wipes ad that has to ship is a tub that stays the tub: foil intact, then lid flipped, same lockup, same lot code neighbourhood, same colourway. That is a bounded motion problem. You already own both stills. Do not prompt a model to invent a second scent while the lid travels.
Frame A is sealed; frame B is the flipped lid
Photograph the tub where it sits — same lens height, same sweep, same label facing camera. Foil or seal in place. That is the first frame. Photograph the same SKU with the lid open, wipe well visible or the stack just broken, still the same badge. That is the last frame.
First-last frame takes those two stills and generates the motion between them. Ordinary image-to-video knows where it begins and improvises the rest. First-last has to land. The arc of the shot is decided by you.
The two frames have to be plausibly connectable in the time available. Same tub, same lighting family, same camera. A hero of the closed tub morphing into a wide of a nursery is a warp, not a lid flip. Keep the tub large in frame. Fine print is the first thing a generator loses. If the scent line must read, it has to fill the frame at both ends.
Do not use a last frame from a different SKU. Lavender sealed into unscented open is a morph of the badge. The model will connect them. The connection is the artefact every buyer notices.
VEO First Last Frame interpolates; it does not reprint the badge
Create a first-and-last-frame transition video is the named agent job: two photos in, one transition out. The agent passes them as first and last frame and picks a first-last-capable model. Cost is priced per model, shown before you confirm. This is not the plain "turn one photo into a video" capability. Missing the open lid is a different job.
VEO First Last Frame is the catalog row for that interpolate: first frame and last frame, native audio, durations 4s / 6s / 8s only, quality including 720p, 1080p, and 4K, 40 credits. It does not invent a tub from a paragraph. There is no ninth second on this row. A lid that seats in two seconds looks padded at eight. If the two stills are not connectable in eight seconds — macro of a badge to a wide of an aisle — the model will warp, not flip.
Audio is on. A silent brief still gets a soundtrack you did not choose. Write the mix (a quiet peel, room tone) or write silence. Plan to replace the bed if you will score later. Do not treat this as a talking-head row. First-last will interpolate a face from pose A to pose B. It will not lip-sync a script about "gentle on skin."
First-last as the product-turn model is the same contract applied to a SKU. The tub is the SKU. Treat it that way.
Prompt the travel, not the scent
Once both stills are attached, the prompt is only travel. Slow locked-off peel. No handheld. No new kitchen. No extra hands unless a real, granted hand is already in both photographs. Do not describe the fragrance, the fibre count, or a claim the photographs already show. The stills are the spec. Language does not pin pixels.
Inspect the midpoint. Ends are held by construction. The middle is where a generator cheats — a second colourway, a badge that swims, a wipe count that changes. If the middle grows a new scent lockup, reroll the interpolation. Do not regenerate both stills "to match the motion." The stills are the contract. The motion is the cheap middle.
One axis per generate. A lid flip or a peel. Two axes at once is how the model blends a flip with a transform. A 180° tub orbit is a different first-last pair (front and three-quarter of the same closed SKU). Do not ask one eight-second file to orbit and unseal.
A loop (same still in both slots) is ambient motion on one plate. This offer needs two states. If you only have the closed tub, shoot the open still. A generated "after" is a different SKU.
This is not the baby-brands /for page
Baby product brands is a parent-in-home surface: unpolished use, one-handed setup, a named parent who agreed to appear. That page is not a tub catalog. An OEM or CPG line that copies its "real nursery at 3am" brief will generate a baby, a private interior, or both. Wipes are a SKU. The job is the lid.
Do not generate a baby. Do not generate a hand wiping a generated infant. That is a private figure and a fabricated proof of use. Real parents, with written consent, on camera, or no people in the ad.
Claims about skin, fragrance-free, or "safe for" stay on the approved labelling. Overlay a line you wrote if the mute autoplay needs a count or a SKU string. Do not ask Veo to typeset "70 wipes" onto a cousin tub. If the count is wrong at the midpoint, you sold a different pack.
FAQ
Can I animate one photo of the sealed tub and hope the lid opens?
You can. The ending is then the model's guess. Wipes is the flipped lid on the same badge. Pin the open tub as the last frame or you are not selling the unseal.
Do the two photos have to be shot on the same day?
They have to share geometry. Same tub, same lens family, same lighting neighbourhood. A noon still into a night still is a time-lapse you should prompt as one. A different colourway is a morph.
Why VEO First Last Frame instead of a talking-head model?
Because the product is interpolation between two approved stills, not a mouth. This row is 4 / 6 / 8 seconds, 4K available, native audio, 40 credits. A presenter row will talk over a tub it invented.
Is this the same as uploading one image to image-to-video?
No. One image is open-ended motion. Two images is a bounded landing. The agent notes that this capability needs first frame and last frame. Missing the open lid is a different job.