40 free credits every month — sign up free, no card Get started
Sign up Log in

Video model

EZ Video 2 Reference

Your character, in motion.

Add pictures of your character, a place or a prop, plus video clips and audio, and EZ Video 2 Reference keeps them recognizable in every frame, with sound. Add a start or end frame when you want an exact opening or closing shot.

Open EZ Video 2 Reference

Consistent character AI video examples, with prompts

Reference image 1: the cartoon fox knightReference image 2: the medieval market
A character and a place“The fox knight from image 1 walks through the busy market from image 2, picks up a red apple from a stall and waves at the camera.”
Reference image 1: the cartoon manReference image 2: the astronaut
Two reference images“The cartoon man from image 1 and the woman from image 2 wave at each other across a sunny park and smile.”
Start frame: the astronaut portrait
Start frame“The woman turns her head, smiles and waves at the camera.”

How reference images keep your character consistent

Characters, places and props

Add up to 9 images of your character, a place or a prop, plus up to 3 videos and 3 audio files. Refer to them in your prompt as [Image1], [Video1], [Audio1].

Reference images or a start frame

Reference images show who and what appears. A start frame is the exact first picture, which then moves the way you describe. You can use both.

Generated sound, cost shown first

Every clip comes with generated sound. Credits are shown on the Generate button before you run. Failed videos are refunded.

EZ Video 2 Reference specs

Length
5 to 15 seconds
Resolution
480p or 768p
Aspect ratio
16:9, 9:16, 4:3, 3:4, 3:2, 2:3 or 1:1; a start frame sets its own shape
Inputs
Up to 9 images of a character, place or prop (an optional start and end frame count toward them), 3 reference videos and 3 audio files; at least one image or video is needed
Audio
Generated sound with every clip
Cost
Credits are shown on the Generate button before you run. Failed videos are refunded.

How to use EZ Video 2 Reference

  1. Add up to 9 reference images, 3 videos and 3 audio files, and optionally a start and end frame.
  2. Write what happens and refer to the pictures as image 1, image 2, for example "The man from image 1 waves at the woman from image 2."
  3. Pick 5 to 15 seconds and 480p or 768p, check the credits on the Generate button, then generate. Failed videos are refunded.
Open EZ Video 2 Reference

EZ Video 2 Reference FAQ

What is EZ Video 2 Reference?

EZ Video 2 Reference is EZ Character's reference-to-video model. It turns up to 9 reference images, 3 reference videos, 3 audio files and a prompt into a 5 to 15 second video with sound.

How do I keep a character consistent in an AI video?

Add clear pictures of your character as reference images and refer to them in your prompt as image 1, image 2 and so on. EZ Video 2 Reference uses them to keep the character recognizable through the clip.

How many reference images can I use?

Up to four. Each one can be a character, a place or a prop. Name them in your prompt as image 1 to image 4.

What is the difference between reference images and a start frame?

Reference images show who and what should appear in the video. A start frame is the exact first picture of the video, which then moves the way your prompt describes.

How long are EZ Video 2 Reference videos, and at what resolution?

Choose 5 to 15 seconds at 480p or 768p. Every clip comes with generated sound.

How much does EZ Video 2 Reference cost?

It uses EZ Character credits. The Generate button shows the total before you run, and failed videos are refunded.

Try EZ Video 2 Reference

Open EZ Video 2 Reference