
Fixed
Red-leather interior
The car and its colour are locked in: the same red-leather seats and open top show up on every run, so the photo does not have to be taken in a car.
Turn one portrait into a red-convertible coffee drive: the driver is yours, and the interior, the cup and the city skyline are already in the clip.
Example · Convertible Coffee DrivePNG / JPG / WebP · up to 10 MB · at least 512px on the short side
0/1 photos
One portrait of the driver, chest up and face visible. The frame is inside the car, so a clear front-facing portrait works best.
Video settings
No prompt needed. Only upload photos of yourself or people who agreed to be featured; celebrity photos and film stills aren't allowed.
A Convertible Coffee Drive AI video puts one portrait behind the wheel of a preset scene: a red-leather convertible interior, a city skyline and a takeaway coffee, with a relaxed lift of the cup. Only the driver is yours — everything else is already fixed.

The value is that the whole lifestyle setup is preset. There is no car to own, no coffee to buy and no crew to film: the clip already has the car, the colour, the city, the cup and the camera, and the photo only supplies the person at the wheel.
A trend directory lists the clip as a “Convertible Coffee Drive” template on 28 October.
A same-name AI video generator page opens at another tool on 30 October.
More template pages pick up the name in the first days of November.
Listing dates from a third-party trend roundup and template pages, read on 4 November 2026; no original social post was found.
Car, colour, city, cup and camera are already set; only the driver is yours. Four frames from the built-in clip show what never changes.

Fixed
The car and its colour are locked in: the same red-leather seats and open top show up on every run, so the photo does not have to be taken in a car.

Fixed
The coffee is a plain takeaway cup already in the clip — no brand, no product to swap in, and nothing to buy for the shot.

Fixed
The city outside the windshield is fixed too: this is not a route or a location picker, and the skyline stays the same in the output.

Fixed
The camera and the one gesture are preset: a slow, relaxed lift of the cup toward the camera. The photo supplies the person making it.
One photo plays the driver, and the car, the city and the coffee are already in the template. There is no prompt field: add the portrait, check the resolution and generate.

Photo 1·The driver
Face, hair and build for the person at the wheel. The photo becomes the driver in the red-leather seat, lifting the cup.
Works well
One person, face clear
Chest up or waist up
Natural, unfilteredAvoid
Two people in one photo
A hand or glasses over the face
Dark, blurry or tinyAdd the driver
Add one clear portrait; it becomes the person behind the wheel.
Click Generate
The button shows the exact price for the resolution you pick before you start.
Post it
The download keeps the 9:16 frame and the clip's own sound, so there is nothing to re-record.
The effect replaces a person at the wheel, so it takes a portrait rather than a pet; a pet driver is not supported here.
Copy a Kling video-edit prompt that puts your portrait behind the wheel of the red convertible clip, or a Seedance prompt that films a new coffee drive from one photo. On this page the prompt is already set, so the portrait is all you add.
Kling 4.0 video edit
Prompt length 919
Use @Video1 as the reference for the whole drive. Replace only the driver, the man with glasses and a beard in the light blue denim shirt and jeans at the wheel of the red-leather convertible, with the person in @Image1.
Preserve the face, hairstyle, hair colour, skin tone, age and build of the person in @Image1; keep glasses only if @Image1 wears them. Transfer the driver's motion from @Video1 frame by frame: one hand on the wheel, the sip from the takeaway cup, the relaxed glance toward the camera and the casual hand gestures that follow.
Keep the red-leather interior, the open top, the plain takeaway cup, the city towers past the windshield, the low passenger-side camera, the single take, the vertical frame, the pacing and the audio of @Video1 unchanged.
Keep one stable face, natural hands with five fingers and the cup in the hand that holds it. No brand on the cup, no extra people, no text or logos.Keep the scene in one line
Car, cup, city and camera are already in @Video1; one sentence keeping them beats describing each one again.
Settle the glasses
The original driver wears glasses; say whether yours stay or go, so the edit does not guess.
Keep the cup plain
“A plain takeaway cup, no brand” keeps a logo from appearing in the middle of the frame.
A car brand
Naming a make redraws the interior and adds badges; the red-leather convertible is already there.
“Drive faster” or stunts
Speed and stunts turn a relaxed coffee run into a risky driving clip that the model will happily render.
A new city
Swapping the skyline re-shoots the background, and the light on the face changes with it.
Asks for a new scene
Me driving a convertible with coffee in the city.
Swaps the driver only
Use @Video1. Replace only the driver with @Image1, keeping glasses only if the photo has them; keep the red-leather car, the plain cup, the skyline and the audio.
The first asks for a new scene. The second edits the clip, swaps only the driver and settles the glasses question.
Every template works the same way: add your photos, press Generate and get a shareable video without writing a prompt.
View all effectsOne photo shows the gear to the camera.
Try itTwo photos cast both parts of the COLORS duet.
Try itClimb the giant 2027 from one photo
Try itPoint, press and swap with a friend
Try itOne dancer edited into three: clone yourself or bring two friends into the 50 Cent trio dance.
Try itThree photos spin through the sunset court dance.
Try itWalk a roaring stadium and calm it down.
Try itUpscale it so the cup and the skyline stay crisp, add seconds to the drive, or lift the driver out of the car for another background.
Generate a clip from a prompt, a still image, a reference or existing footage.
Open toolCut the subject out of any clip and export a transparent WebM or a solid colour.
Open toolFAQ
No, each video costs credits. The price follows the resolution you pick, and the Generate button shows it before you start. New accounts start with 10 credits.
No confirmed original post has been found. The name first appears as a template-directory listing in late October 2026, so this page treats it as a preset scene, not a viral trend.
No. The car and its interior are already in the built-in clip; the photo only supplies the person at the wheel.
No. The car, its colour and the city skyline are fixed, so there is no car, route or location picker.
No. It is an AI-generated scene, not a real driving record, and the clip is not a guide. Do not drink or film while driving in real life, and do not post the video as if it were real.
Hands, fingers and the rim of a moving cup are common quality checks in generated video, and a run can still drift. A clear, front-facing portrait keeps the driver close to the original, but nothing guarantees the cup in every frame.
15 seconds. The length follows the built-in clip and is not adjustable.
Yes. The frame follows the built-in clip, which is 9:16, so the output is vertical and there is no separate setting to change.
Both are on offer and nothing else changes with them: same clip, same 9:16 frame. The price difference is on the button before you generate.
Yes. The template recasts the built-in clip, so the sound that plays in it is the sound in your video.
No. This is a fixed template: the scene, the camera and the cup are already set, so there is no prompt field to fill in. The prompts above are for running the drive in another tool.
No. The slot replaces a person at the wheel, so the template takes one portrait rather than a pet photo.
No. The cup is a plain takeaway cup, and the template does not add a brand, product text or a sponsorship.
It is not a product shot. The template does not guarantee packaging, branding or product accuracy, so it cannot stand in for a real product shoot.
Convertible Coffee Drive
Add one portrait, check the resolution and the price, and generate: the red-leather interior, the cup and the city are already in the clip.