Convertible AI Video: The City Cruise, Starring You
You are at the wheel of an open-top convertible with red leather seats, skyscrapers sliding past, taking a long sip of takeaway coffee and waving a finger to the music. One photo of you is all it takes.
Updated : Page published.
1Add your photo
What you'll get
Front-facing, well-lit selfies work best. One face per photo.
2Choose quality
By generating you confirm you have permission to use the people in your photos. Terms
No subscription needed · Ready in about 3 minutes · Failed renders are free
The convertible coffee drive is a 15-second AI video in which a person cruises past city skyscrapers in an open-top car with red leather seats, sipping a takeaway coffee and waving a finger to the music; videosi makes it from one photo of you.
- Fast facts
- First seen
- Stage
- Just starting
- Started on
- AI template pages (unconfirmed)
- Sound
- No single confirmed sound. Posts in the wider convertible drive format use different songs.
- Meaning
- The convertible coffee drive is a short AI video in which a person cruises past city skyscrapers in an open-top car with red leather seats, sipping a takeaway coffee and moving to the music.
- Related trends
- That Boy That Boy Dance AI, Carpool Karaoke AI
Page updates
- November 1, 2026 — Page published.
The Convertible AI Video prompt and model
Convertible AI Video is made with Seedance 2.0 / 2.5 (you pick the tier) by ByteDance. The prompt behind it has 5 parts, and the timing is what makes or breaks it.
- Model
- Seedance 2.0 / 2.5 (you pick the tier)
- Mode
- Photo + motion reference to video
- Length
- 15 seconds, 9:16, 1:1 or 16:9
- Input
- 1 photo
- Identity lock Your photo is the only source for the face, hair, skin tone, build and clothes, and nothing of the reference driver stays.
- Motion reference A 15-second clip supplies the low passenger-side camera, the gestures and the timing.
- Car and city An open-top car with red leather seats, a dark dashboard and skyscrapers passing overhead.
- Timeline Six beats, from the glance at the lens to the long sip to the hands moving with the music.
- Rules One person, one cup, five fingers per hand, one hand on the wheel, no logos, plates or text.
Replace the young man with shoulder-length wavy brown hair, a white shirt and dark jeans in Video 1 with the person from Image 1.…
Why it goes wrong when you do it yourself
- Without a motion reference the low camera turns into an ordinary dashboard shot and the look is gone.
- The cup often gains a second copy or melts into the hand during the long sip.
- The driver's hair and shirt from the reference can stay unless the prompt names them and rules them out.
- Each try costs model credits and several minutes, and a 15-second clip gives the face more time to drift.
Convertible AI Video examples
How to make your Convertible AI Video video
Upload one photo of yourself
Face to the camera, head and shoulders or more in frame, even light. Your hair and what you are wearing in the photo are what you wear in the video.
Pick the model and the format
Choose the model and resolution, then 9:16 for TikTok, Reels and Shorts, 1:1 for a square post or 16:9 for a wide cut.
Generate and download
Press Generate and the 15-second clip is rendered for you. It is an MP4 with no watermark and the sound of the reference clip already on it.
Post it
Post it as it is or swap in your own song in the app you post from. Turn on the platform's AI-generated label.
What is the Convertible AI Video trend?
Updated · videosi is an independent tool. It is not affiliated with TikTok, Instagram, YouTube, or with the owners of any trend, song, game or brand named on its pages.
The convertible coffee drive is a short AI video built around a mood rather than a stunt. The camera sits low near the passenger seat and looks up across an open-top car with red leather seats. The driver glances at the lens, tips a takeaway cup back for a long sip, then waves a finger and a free hand to the music while city towers slide past overhead.
It has only just started to spread. The name appears on AI template pages from October 2026, and we have not found one original TikTok post or a creator who started it, so its origin is unconfirmed. Two older habits feed it: people posting real iced coffee runs with the roof down, and CapCut and Dreamina templates from 2026 that put you behind the wheel of a convertible you do not own. Examples are still few, and the clips below that show no coffee are the wider convertible drive format.
Nobody films this version. It is generated by an AI video model from one photo of you, a 15-second reference clip that supplies the camera angle, the car and the movement, and a written prompt. Your face, hair and clothes come from your photo; the red seats, the skyline and the coffee come with the effect.
The appeal is simple: it looks like a morning you would like to be having. Treat it as a fantasy clip. In a real car, keep both hands free for driving and have your coffee parked.
Convertible AI Video: shot by shot
- 0–2 s
The glance
Low camera near the passenger seat. You look over at the lens with the cup in your hand as the shot settles.
- 2–4 s
The long sip
You tip the takeaway cup right back, one hand on the wheel, towers sliding past behind you.
- 4–5 s
Cup down
The cup comes down and your eyes go back to the road ahead.
- 5–9 s
One finger up
One finger rises and waves in time with the music while the cup stays in the same hand.
- 9–13 s
Hands to the beat
The free hand points and sweeps to the beat, as if you are talking the song through to yourself.
- 13–15 s
Cup at the chest
The cup comes up to your chest and you look back toward the lens as the clip ends.
Tips for a better result
Show your torso, not just your face
The camera sees your chest, arms and lap. A photo cropped tight to the face leaves the model to invent your clothes and arms.
Choose clothes that stand out from red
Red seats fill the frame. White, denim, black or pale colours read clearly; a red top melts into the seat.
Leave sunglasses off
The glance at the lens is the first thing people see. Covered eyes make the likeness drift.
Use daylight photos
The clip is set in flat city daylight. A daylight photo matches it better than a dark indoor shot.
Good to know before you make a Convertible AI Video video
- The car, the red seats, the city and the coffee are built in. This page does not put your own car or your own location in the clip.
- Hands and the cup are where invented detail shows first, especially during the long sip.
- The clip comes with the sound of the reference clip on it; the mouth does not follow any lyrics, and likeness is not guaranteed. A failed, timed-out or blocked render returns its credits automatically.
- This is a generated fantasy clip. Do not copy it at the wheel of a real car: sip your coffee parked.
Convertible AI Video: questions
What is the convertible coffee drive AI trend?
The convertible coffee drive is a 15-second AI video of a person cruising past skyscrapers in an open-top car with red leather seats, sipping a takeaway coffee and waving a finger to the music. The name appears on AI template pages from October 2026. No original creator is confirmed. videosi makes it from 1 photo.
How do I make a convertible coffee drive video from a photo?
To make a convertible coffee drive video on videosi, upload 1 photo of yourself, choose the model, resolution and 9:16, 1:1 or 16:9, and press Generate. The 15-second video renders in a few minutes and you can close the page, because the result waits in My creations. You write no prompt.
Is there a website or generator for the convertible coffee drive?
Yes. videosi (videosi.io) is a web tool that makes the convertible coffee drive from 1 photo. The car, the camera, the movement and the prompt are built in, so you choose only the photo and the format. It makes a 15-second MP4 with no watermark, and you need no app.
Is there a TikTok filter or CapCut template for the convertible coffee drive?
We could not confirm a template with this exact name as of November 2026, although CapCut and Dreamina have general convertible driving templates, and apps change often. videosi is independent and not affiliated with TikTok, CapCut or Dreamina. Its convertible coffee drive page is a web tool: add 1 photo and download an MP4.
What AI model or prompt makes the convertible coffee drive video?
The convertible coffee drive on videosi is made with ByteDance's Seedance video model (Seedance 2.0 Mini by default; Fast, Pro and Ultra are one click away), from a written prompt plus a 15-second motion reference. Doing it yourself takes several tries, because the cup and hands distort. On videosi the prompt and reference are built in.
How much does the convertible coffee drive cost, and is it free?
The convertible coffee drive on videosi is not free. A 15-second video costs 13 credits on the Standard model at 720p, and an account's first video costs no more than 10. Credit packs start at $6.99 for 10 credits and never expire. Purchases are final; a failed render returns its credits automatically.
Why did my convertible coffee drive video come out wrong?
The usual causes are a photo cropped tight to the face, sunglasses, a dark photo or a red top that melts into the seats. For the videosi convertible coffee drive, use a front-facing daylight photo that shows your torso. Likeness is not guaranteed in a 15-second clip. A failed, timed-out or blocked render returns its credits automatically.
Can I use someone else's photo or a pet?
You can use a photo of another adult who has agreed to it. videosi does not accept celebrities, public figures or minors for the convertible coffee drive, and users must be 18 or older. The effect is written for 1 person at the wheel, so it is not made for pets, and photos and results are deleted within 30 days.
What does "convertible coffee drive" mean?
"Convertible coffee drive" describes exactly what the 15-second clip shows: a takeaway coffee, a car with its roof down and a slow cruise through a city. It has no deeper meaning that we can confirm. The appeal is the relaxed, slightly showy morning that the viewer would like to be having, and videosi puts you in it.
What song is used in the convertible coffee drive?
No single song is confirmed for the convertible coffee drive as of November 2026, and clips in the wider convertible drive format use different music. The videosi video comes with the sound of its reference clip on it, so you can post it as it is or swap in your own song where you post.
Is the convertible coffee drive still trending?
As of November 2026 the convertible coffee drive is just emerging. The name appears on AI template pages from October 2026, and we have found few finished clips and no single viral post. That can change quickly, and videosi updates this page when it does, so check the current posts on TikTok too.
Can I choose my own car or city?
Not on this page. The videosi convertible coffee drive uses one built-in look: an open-top car with red leather seats, a dark dashboard and a city of skyscrapers, without badges or readable plates. You choose the photo, the model and the format, and your hair and clothes come from your photo.
Is it safe to drink coffee while driving like in the video?
The convertible coffee drive on videosi is a generated clip and nobody drives to make it. Do not copy it in a real car: keep your attention on the road and your hands free for driving, and have your coffee parked. Local laws on distracted driving differ, so check the rules where you live.
Can I make it on my phone?
Yes. videosi runs in the phone browser, so there is no app to install. Open the convertible coffee drive page, add 1 photo from your camera roll (HEIC from an iPhone works), press Generate and download the 15-second MP4 to post on TikTok, Reels or Shorts.
Trending this week
All trends this week
Make your Convertible AI Video video
Upload a photo and press Generate. 13 credits, refunded if it fails.
Get the next trend first
One email when new trends land on videosi, about once a week. Unsubscribe in one click.
See videosi first on Google
Add videosi as a preferred source and our trend pages show up first in your Top Stories and AI answers on Google.