RefVid
Video templates

A travel vlog, starring you

Save yourself once from a few photos and RefVid films the travel vlog you didn’t have time to shoot: walking a sunny old-town street with the camera in hand, a line to the viewers, then turning the camera to the view. Your face stays the same in all three shots.

10 s · 9:16 · with sound

Use this template

Sign in, add your subject, and the studio opens with this template filled in. Your first 3-second clip is free: this template’s first shot.

Made from these photos

Made with RefVid on Kling 3.0 Omni from 4 reference photos of Mia (an AI-made subject), with this template's prompt.

What you get

  • You from 1–5 photos, the same face in every shot
  • 3 shots, 10 seconds, vertical 9:16
  • Your spoken line and street sound generated with the video
  • No watermark

Who it’s for

For travel creators who want content from trips they didn’t film, for tourism boards and hotels showing a place with a friendly guide, and for anyone planning a trip who wants to picture themselves there.

The prompt

What the studio fills in for you. Your subject takes the place in brackets; you can change any of it.

  1. Shot 1Handheld vlog shot: [you] walks down a sunny cobbled old-town street lined with cafés and pastel houses, holding the camera at arm’s length, smiling. Street sounds, light breeze.
  2. Shot 2[you] stops by a fountain and says to the camera: "Okay, this little street is my favourite thing so far."
  3. Shot 3[you] turns the camera around to reveal a wide view over terracotta rooftops to the sea at golden hour.

Make it yours

  • Pick the city

    Name a real place in each shot, such as Lisbon’s Alfama, Kyoto’s Gion or your home town’s market street.

  • Say your line

    Replace the quoted line with your own reaction, a tip for viewers, or the name of the café you just found.

  • Change the ending

    Swap the rooftop view for a sunset over a harbour, a mountain lake or a night market lighting up.

Photos that work best

People: 1–5 photos with the face clearly visible and evenly lit — a straight-on portrait first, then a three-quarter angle and a profile. Skip sunglasses, heavy filters and group shots; if a photo shows more than one person, the studio can’t tell who you mean.

How it works

  1. Sign in and add you from 1–5 photos. Each subject is saved once, so every later template takes one tap.
  2. The studio opens with this template filled in: all 3 shots, 10 seconds, 9:16. Change any word you like.
  3. Press Generate. The clip is ready in a few minutes, without a watermark, and the same subject is there for the next one.

Questions

Can I pick the city?
Yes: the place is in each shot’s prompt. Write Lisbon, Kyoto or your home town before you generate; real landmarks work, famous people don’t.
Can I change what I say?
Yes, the line is in quotes in the second shot; replace it with yours.
How much does this template cost?
A new RefVid account’s free credits cover one 3-second clip. The full template is 10 seconds with sound: buy it as a single video, with no plan, or use credits from a pack or plan. Current prices are on the pricing page.
Is this an AI travel video generator for any city?
Yes: name the place in each shot. Real cities and landmarks work; famous people don’t.