Describe the scene, the camera movement and the mood in plain language, and Seedance 2.5 turns it into a video clip. The more specific the prompt, the more control you have over the result.
IAllegro
Seedance 2.5 AI Video Generator
Create videos with Seedance 2.5, ByteDance's newest Seedance model, right in your browser. Start from a text prompt, a first and last frame, or up to nine reference images, and get a 4- to 15-second video with sound in 480p, 720p or 1080p.
Current modelSeedance 2.5
Example videos
Examples of what the Seedance 2.5 model can produce. On Sonata AI you can generate clips of 4 to 15 seconds in 480p, 720p or 1080p.
Adagio
Text, image and sound in one model
Seedance 2.5 is the newest model in ByteDance's Seedance family. On Sonata AI you can use it for text-to-video, image-to-video from a first and last frame, and reference-image video, with sound generated along with the picture.
Adagio
How to create a video in four steps
Everything happens on this page, in your browser.
Adagio
Prompt tips for better results
A clear prompt leaves the model less to guess.
Coda
Seedance 2.5 FAQ
Common questions about using Seedance 2.5 on Sonata AI.
01What is Seedance 2.5?
Seedance 2.5 is the latest video generation model in ByteDance's Seedance family, following Seedance 2.0. It creates videos from text prompts or images. On Sonata AI you can use it in your browser with a Sonata AI account.
02How many credits does Seedance 2.5 use?
A 5-second video costs 440 credits at 480p, 990 at 720p and 2,490 at 1080p; a 10-second video costs 880, 1,980 and 4,980. Other lengths from 4 to 15 seconds follow the same per-second rate. The cost is shown on the Generate button before you submit.
03What's the difference between Seedance 2.5 and Seedance 2.0 on Sonata AI?
Seedance 2.5 is ByteDance's newer model. Seedance 2.0 is still available on its own page and uses fewer credits per video (from 200 credits for 5 seconds at 480p), so you can choose based on your budget and the result you want.
04Do Seedance 2.5 videos include sound?
Yes. Videos are generated with audio by default, so each clip comes with sound that matches the scene. If you want a silent clip, switch Sound off before you submit.
05Can I start from my own image?
Yes. Under Start from, choose First frame and upload an image. Seedance 2.5 uses it as the first frame of the video and follows your prompt from there. You can also add a last frame, or choose Reference images to upload up to nine.
06Is Sonata AI affiliated with ByteDance?
No. Seedance is a trademark of ByteDance. Sonata AI is an independent platform that offers Seedance 2.5 generation alongside other video and image models.