A video from a start photo and an end photo
Upload where the shot begins and where it should end. The camera travels from your first photo and lands exactly on the second — one smooth move, no cuts. One photo works too.
What you get
Your shot, from your first frame to your last
01
Lands on your end photo
The camera starts on your first photo and finishes exactly on the second, so the video ends where you chose.
02
Pick a move or write your own
Ready-made moves — orbit, walk through, push in, rise up — or your own prompt, in any language.
03
Your length, your sound
From 3 to 15 seconds, silent or with quiet ambient sound. The price updates as you choose.
04
Any shape
The video follows your start photo: landscape for listings, vertical for Reels and TikTok, or square.
How it works
From two photos to one video in three steps
01
Add a start photo and an end photo
Two views of the same space from different spots work best — the corner of a kitchen and the view down its island.
02
Choose the move
Tap a camera move or write your own prompt, then pick the model, the length and the sound.
03
Create and download
The video is saved to your Library, ready to post or to cut into a longer film.
Before you upload
Which photos work best
Works best
- Two photos of the same space, taken from different spots.
- Both photos in the same light and the same orientation.
- A clear subject between them — a kitchen island, a sofa, the front door.
Avoid
- Two rooms with no way through from one to the other.
- A tight close-up as the start and a wide view from somewhere else as the end.
Stays the same
The video starts on your first photo and ends on your second. Everything in them stays as photographed.
Photo to Video FAQ
Do I need an end photo?
No. With one photo the camera makes the move you pick. The end photo is what makes the shot land exactly where you want it.
What makes a good pair of photos?
Two shots of the same space from different spots, in the same light. Very different photos, such as two rooms that are not connected, can make the video cut instead of move.
How is this different from Cinematic Motion?
Cinematic Motion takes one photo and a ready-made camera move. Photo to Video adds the end photo, your own prompt, and a choice of model, length and sound.
How long can the video be?
3, 5, 8, 10 or 15 seconds with Kling v3, or 5 or 10 seconds with Kling 2.6.
Can the video have sound?
Yes, with Kling v3: quiet ambient sound that matches the scene, for a few extra credits. Kling 2.6 makes silent videos.
Can I use it from ChatGPT or Claude?
Yes. Photo to Video is a tool on the Pixly MCP server and the API, at the same prices as in the app.
Related video tools
Photo to Video is one shot between two views. These are the ready-made move, the walk through a whole home and the transformation.
Make the shot you pictured
Add a start photo and an end photo and let the camera travel between them.