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

Video model

Seedance 2.5

Picture and sound, in one take.

Describe a scene and Seedance 2.5 makes the video and its sound together: spoken lines, effects and music. Keep your character on model with up to four reference images, or start from your own first frame.

Open Seedance 2.5

Seedance 2.5 examples with prompts

Reference image of the cartoon fox knight
One reference image, with dialogue“The fox knight from [Image1] pushes open the door of a busy, candle-lit tavern, stops, looks at the camera and says "Who ordered the dragon?" The crowd behind him bursts out laughing.”
Text to video, with sound“A friendly orange cat chef in a tiny kitchen flips a pancake, looks at the camera and says "Breakfast is served!"”
Reference image of the cartoon mascot
One reference image, audio off“The mascot from [Image1] waves hello and does a little hop on a sunny street.”

What Seedance 2.5 can do

Up to four reference images

Add up to four reference images and name them in your prompt as [Image1] to [Image4] to keep a character or object on model. Or start from one first-frame image.

Dialogue, effects and music

Sound is generated with the picture. Put spoken lines in double quotes, or turn audio off for a silent clip.

4 to 30 seconds, cost shown first

Choose any length from 4 to 30 seconds at 480p or 720p. Credits are shown on the Generate button before you run. Failed videos are refunded.

Seedance 2.5 specs

Length
4 to 30 seconds
Resolution
480p or 720p
Aspect ratio
16:9, 9:16, 4:3, 3:4 or 1:1; a first frame sets its own shape
Inputs
A text prompt, one first-frame image, or up to 4 reference images named [Image1]–[Image4]
Audio
Dialogue, effects and music generated with the video; can be turned off
Cost
Credits are shown on the Generate button before you run. Failed videos are refunded.

How to use Seedance 2.5

  1. Open Seedance 2.5 and describe the scene: who is in it, what happens, the camera, and any spoken lines in double quotes.
  2. Optionally add a first-frame image or up to four reference images, named [Image1] to [Image4] in your prompt. Then pick a length from 4 to 30 seconds and 480p or 720p.
  3. Check the credits on the Generate button and generate. Failed videos are refunded.
Open Seedance 2.5

Seedance 2.5 FAQ

What is Seedance 2.5?

Seedance 2.5 is an AI video model that generates the picture and its sound together. On EZ Character it makes 4 to 30 second videos at 480p or 720p from a text prompt, a first-frame image or up to four reference images.

Does Seedance 2.5 generate audio?

Yes. Dialogue, sound effects and music are generated together with the video. Put spoken lines in double quotes in your prompt, or turn audio off for a silent clip.

How long can a Seedance 2.5 video be?

You choose any length from 4 to 30 seconds per video. Output is 480p or 720p.

How do reference images work in Seedance 2.5?

Add up to four reference images and name them in your prompt as [Image1], [Image2], [Image3] and [Image4], for example "The mascot from [Image1] waves hello." This keeps your character or object on model in the new video.

Can I start a Seedance 2.5 video from my own image?

Yes. Upload one image as the first frame and describe the motion and sound you want. A first frame is used on its own, without reference images.

Should I use Seedance 2.5 or EZ Video 2 Reference?

Both keep a character consistent from reference images and add sound. Seedance 2.5 makes longer clips, 4 to 30 seconds, and speaks lines you put in double quotes. EZ Video 2 Reference makes 5 to 15 second clips at 480p or 768p and can combine up to 9 images with reference videos, audio and start and end frames.

How much does Seedance 2.5 cost on EZ Character?

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

Try Seedance 2.5

Open Seedance 2.5