A clip with no footage
Text to video starts from the sentence. There is no file to upload.
Image to video turns one still into a short clip.
OpenWrite a short clip from a sentence, or start that clip from a still you upload. This page does not stop at a still image.
This model does not take a reference image.
Audio is included. This model does not turn it off.
Write a prompt.

An AI video generator on photoeditor is the clip desk. One path starts from a sentence and returns a short video. The other starts from a still you upload and moves that picture.
Length, quality, and the credit count for that combination sit next to the prompt. You read the cost before the run. The page only offers video models that already have a public price in the catalog.

A sentence is enough when you need a clip and you do not have footage. A still is the better start when the product, the room, or the person has to match a picture you already own.
The same account pays for stills and clips. Monthly credits last a month, yearly credits last a year, and a credit pack does not expire. A failed clip returns the credits it spent.

Choose Text to video to start from words, or Image to video when you have a still. Pick a model, then the length and quality that model offers. The generate button shows the credits for that exact combination.
Describe the motion in one sentence. On the photo path, upload the still first. When the clip arrives, download it. A later pass is a new run.

Text to video does not need a source file. Name the subject, the camera move, and what should stay still. The generator returns a clip at the length and quality you selected.
Shorter and longer settings are separate prices when the model bills them that way. The button updates before you start, so the charge matches the controls on screen.

Image to video keeps the uploaded picture as the opening frame and follows the motion you describe. Use it when the object has to stay the object in the photo.
One still goes in. The credit count is the video model, length, and quality together. If the motion is wrong, change the sentence and run again.

A product turn, a slow push-in, and a short loop do not need the same duration. Pick the length the model lists. The page does not offer a duration that has no catalog price.
Queue size and how long finished clips stay in the account follow the plan or pack on the account. Download a clip when you want a copy you control.

Text to video starts from the sentence. There is no file to upload.
Image to video keeps that picture as the opening frame.
The controls show lengths and qualities that model can bill.
Credits on Generate match the model, length, and quality.
Text to video starts from words. Image to video starts from a still.
Each video model shows credits for the settings on screen.
Those controls change the number on the button.
Download the clip. A failed run returns the spend.
Lite $17 / Plus $33 / Pro $72 — full list on pricing
Yes. The generate button names the credits for the video model, length, and quality you selected, before the run starts.
A failed run returns its credits on its own. You do not need to request them.
Yes, when you own the source. On the photo path that is the still you uploaded. The same commercial-use line is on every plan and pack.
Download the clip, or take a still from it and run Image to video again. A new run spends the selected model's credits again.
No. Both paths here return a clip. A still with no motion belongs on the AI image generator.