50% OFFClaim 50% Off
Nano Banana AINano Banana AI

Nano Banana 2.1 is live — sharper edits, cleaner text, up to 4K

Seedance 2.0 AI Video Generator

The previous-generation Seedance engine — dependable text and reference-driven video up to 4K with native audio.

See pricing
Text to Image Image to Image Multi-Reference Editing Character Consistency Up to 4K
5 credits
0/2000

Avoid copyrighted characters, logos, music and sensitive or explicit content — it may be blocked.

Resolution
Aspect Ratio
1

Estimated cost: 5 credits

Your creation appears here

Pick a model, describe the shot, and hit Generate.

Why Seedance 2.0

Why creators choose Seedance 2.0

Seedance 2.0 is the Seedance model to use when you want 4K output and reference-driven control.

Up to 4K

Final-delivery resolution, with 480p to 1080p for drafts.

Reference to video

Up to nine images, three videos, and three audio clips steer the shot.

Optional audio

Generate sound with the picture, or switch it off.

Predictable results

A mature model with dependable prompt adherence.

Seedance 2.0 guide

Everything you can do with Seedance 2.0

Seedance 2.0 is ByteDance’s previous-generation video model, still a dependable choice in the Nano Banana AI studio when you need up to 4K output and reference control. This guide covers its strengths and where it fits against Seedance 2.5 and Seedance 2.0 Fast.

What Seedance 2.0 is built for

Seedance 2.0 offers text to video, first and last frame to video, and multimodal reference to video. Clips run from 4 to 15 seconds at 480p, 720p, 1080p, or 4K (3840x2160), with an optional audio track generated alongside the picture. Aspect ratios include 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and adaptive.

In reference mode you can attach up to nine images, three videos, and three audio clips to steer the subject, wardrobe, motion, and sound of the shot. Frame mode and reference mode cannot be combined in one run, so choose whichever fits the brief.

4K output

The only Seedance tier with a 4K (3840x2160) option, useful for final exports.

Multimodal references

Nine images plus three videos and three audio clips.

Optional audio

Generate synchronized sound or turn it off.

Prompting tips

Describe one subject doing one clear thing, then add the camera and light. For references, label each image in the prompt, for example "the woman from reference one walks through the market from reference two". Without labels, the model has to guess how the images relate.

Seedance 2.0 compared with 2.5 and 2.0 Fast

Choose Seedance 2.0 when the deliverable needs 4K. Choose Seedance 2.5 for longer clips of up to 30 seconds and up to 30 reference images. Choose Seedance 2.0 Fast to draft cheaply before committing to a higher-quality render.

How to use Seedance 2.0

How to use Seedance 2.0 in three steps

Name the subject, action, camera, and light. Label any references you attach.

00:0000:1500:30

Who uses Seedance 2.0

Who uses Seedance 2.0 for video work

Video editors

Video editors

Pickup shots and b-roll at delivery resolution.

Social teams

Social teams

Vertical and square cuts from a single concept.

Product teams

Product teams

Showcase clips with consistent product references.

Indie creators

Indie creators

Short films and music visuals with a steady look.

FAQ

Seedance 2.0 FAQ

What can Seedance 2.0 do?
Text-to-video, and reference-to-video at 480p, 720p, 1080p, and 4K, 4–15 seconds per clip, with optional audio.
How do references work?
Add up to 9 reference images to steer subject, wardrobe, and motion across the shot.
Seedance 2.0 vs 2.5?
2.5 adds longer clips (up to 30 seconds) and up to 30 reference images; 2.0 adds a 4K output option.
Does Seedance 2.0 cost credits?
Yes — per-second billing; the estimate is shown before each run.

Your next visual is one prompt away

Free credits on signup. No card required.