Cash-for-cars is a driveway first-last
Car in frame A, empty drive in B. Interpolate.
Car in frame A, empty drive in B. Interpolate.
Cash-for-cars is not a founder talking over a lot. The offer is disappearance: the wreck is here, then it is gone. That is a bounded motion problem. You already own both stills. Do not prompt a model to invent the driveway.
Frame A is the car; frame B is the empty drive
Photograph the vehicle where it sits — same lens height, same kerb, same house behind it. That is the first frame. Photograph the empty pad after the tow, or composite the empty pad from a second still of the same geometry. 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 location, same lighting family, same camera. A close-up of a bumper morphing into a wide empty street is a warp, not a pickup. Keep the driveway.
Interpolation is the ad
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.
Flux 3 First Last Frame to Video is the catalog row for that interpolation: start frame and end frame, native audio, 720p or 1080p, durations from 5 seconds through 20. The listed rate is 9 credits per second. Audio is on — write the mix (a tow rumble, a quiet pad) or write silence. A silent brief still gets a soundtrack you did not choose.
Prompt the travel, not the objects. The stills already contain the car and the empty concrete. Name the mechanism: hold, then the vehicle leaves frame; camera locked; no new house. If the endpoints share geometry, the morph reads as a pickup. If they do not, you get a mushy crossfade you could have made in an editor without a video bill.
What this is not
It is not a talking buyer. It is not a text-to-video "old sedan vanishes from suburban driveway" paragraph that rebuilds the street. It is not a single-image wiggle that leaves the wreck sitting there for eight seconds of steam.
Do not use a last frame that is a different property. The model will connect them. The connection is the artefact everyone notices.
Do not treat a loop (same still in both slots) as a cash-for-cars ad. A loop is ambient motion on one plate. This offer needs two states.
If you needed a founder line about paperwork, that is a different generate, cut after the empty drive. The driveway shot does not have to talk.
FAQ
Can I animate one photo of the car and hope it leaves?
You can. The ending is then the model's guess. Cash-for-cars is the empty pad. Pin the empty pad as the last frame or you are not selling the pickup.
Why Flux 3 instead of a talking-head model?
Because the product is interpolation between two approved stills, not a mouth. Flux 3 first-last is 5–20 seconds, 720p/1080p, native audio. A presenter row will talk over a driveway it invented.
Do the two photos have to be shot on the same day?
They have to share geometry. Same drive, same lens family, same lighting neighbourhood. A noon still into a night still is a time-lapse you should prompt as one. A different house is a morph.
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 empty drive is a different job.