Nana Banana Pro
Prompt
0/2500
Public Visibility

Seedance creations

No preview yet

Adjust the settings on the left and generate a video to get started.

Runs Seedance 2.0, Fast and Mini — the Seedance models our provider routes today. Seedance 2.5 joins the model list as soon as the API opens.

Released · Integration in progress

Seedance 2.5 AI Video Generator

ByteDance's Seedance 2.5 generates 30 seconds of synchronized audio and video in a single pass, from up to 50 reference files, with timestamp-level editing. We're integrating it — the generator above runs Seedance 2.0 today.

30s Audio + Video in One Pass
50 Reference Files
Timestamp-Level Editing

What's New in Seedance 2.5

Seedance 2.5 raises the ceiling on every part of the pipeline: longer single-pass output, far more references, and editing you can aim at a specific moment.

30-Second Single-Pass Output

Seedance 2.5 generates a full 30-second clip in one pass, up from 15 seconds. Multi-round extension carries that out to several minutes while holding characters, environment and narrative pacing steady.

Joint Audio-Video Generation

Audio and visuals come out of one unified multimodal architecture, so sound and picture are aligned from the first frame. Seedance 2.5 keeps that alignment across extension rounds.

30 Images, 10 Videos, 10 Audio Clips

One pass accepts up to 30 reference images, 10 video clips and 10 audio clips. That is the 50-reference figure, broken down — video and audio are first-class references, not just style hints.

Timestamp-Level Editing

Point Seedance 2.5 at a time range and change the narrative, camera, movement or rhythm inside it. Characters, actions and plot in a specific clip can be revised after the video exists.

Clay-Render Blockout

Feed in a textureless 3D model to lock spatial structure, character poses, motion paths and camera angles. Seedance 2.5 reads the blockout and derives light direction, colour temperature, intensity and shadow from it.

Green Screen & Camera Editing

Replace a background while the subject stays intact, with clothing, hair, gait and lighting responding physically. Camera movement can be re-aimed without disturbing the performance underneath.

Seedance 2.5 vs Seedance 2.0

Seedance 2.5 keeps 2.0's joint audio-video architecture and pushes length, references and editing control well past it. The Seedance 2.0 column is what the generator on this page does right now.

Single-pass length
2.5 · Up to 30 seconds
2.0 · 4–15 seconds
2x

One continuous 30-second take replaces a stitched sequence of short shots.

Long-form output
2.5 · Multi-round extension to several minutes
2.0 · Stitch clips yourself
New

Extension rounds carry characters, environment and pacing forward, so a multi-minute video holds together.

Audio
2.5 · Joint audio-video, in sync
2.0 · Joint audio-video, in sync

Same unified architecture in both. Seedance 2.5 adds sync that survives extension rounds.

References per pass
2.5 · 30 images + 10 videos + 10 audio clips
2.0 · Up to 9 reference images
Biggest jump

Video and audio become reference material in their own right, not just an image board.

Editing control
2.5 · Timestamp, green screen, camera perspective, reference-based
2.0 · Prompt and reference driven
New

Editing moves from re-rolling a prompt to aiming at a moment, a subject or a camera path.

Blockout control
2.5 · Clay-render 3D references
2.0 · Not available
New

Camera position and staging can be locked before generation instead of coaxed out of a prompt.

Resolution
2.5 · Not stated at launch
2.0 · Up to 4K, 10-bit colour

Native 4K with 10-bit colour was the Seedance 2.0 upgrade. The Seedance 2.5 launch post states no resolution, so don't read 4K into 2.5 yet.

Available on this page
2.5 · Not routable yet
2.0 · Live in the generator above

Seedance 2.5 appears in the model list the day our provider opens the route.

Seedance 2.5 Video Demos

Real Seedance 2.5 output posted publicly on X, embedded with attribution intact.

How to Use Seedance on This Page

The same workflow transfers to Seedance 2.5 when the route opens. Build it now on Seedance 2.0.

1

Pick a mode and a model

Choose text-to-video, image-to-video or reference-to-video, then Seedance 2.0 for maximum quality, Fast for speed, or Mini for volume.

2

Write the shot, not the summary

Name the subject, the action, the camera move and the light in one line. Add reference images to hold a character or a look steady across takes.

3

Set duration, ratio and audio

Pick 4 to 15 seconds, an aspect ratio from 21:9 through 9:16, and leave audio generation on. Finished videos land in Creations and stay there.

Can You Use Seedance 2.5 Here Yet?

Seedance 2.5 has shipped. Our upstream provider hasn't opened the route, so this page runs Seedance 2.0 until it does — and switches over the day it opens.

Released by ByteDance

The official Seed launch post documents 30-second single-pass audio-video, the 30 + 10 + 10 reference breakdown, timestamp editing and clay-render blockout.

API access is still rolling out

ByteDance lists Seedance 2.5 API access as coming soon. Until an upstream route exists, no third-party tool can honestly call Seedance 2.5 — including this one.

Live here today: Seedance 2.0

Seedance 2.0, Fast and Mini run in the generator above with text, image and reference input, 4 to 15 second clips, up to 4K on the standard tier, and audio generation on by default.

August 2, 2026

FAQ

Seedance 2.5 Frequently Asked Questions

What Seedance 2.5 does, what changed since 2.0, and when you can run it here.

1

What is Seedance 2.5?

Seedance 2.5 is ByteDance's video generation model. It produces a 30-second clip with synchronized audio in a single pass, accepts up to 30 reference images, 10 video clips and 10 audio clips, and supports timestamp-level editing of narrative, camera, movement and rhythm.

2

What's new in Seedance 2.5 compared with Seedance 2.0?

Single-pass length doubles from 15 to 30 seconds and extends to several minutes across rounds. References grow to 30 images plus 10 video and 10 audio clips. Editing gains timestamp targeting, green-screen replacement, camera-perspective changes and clay-render 3D blockout.

3

How long can a Seedance 2.5 video be?

Thirty seconds in one pass. Longer pieces are built with multi-round extension, which carries characters, environment and narrative pacing forward so a multi-minute video stays consistent shot to shot.

4

Does Seedance 2.5 generate audio?

Yes. Seedance 2.5 uses a unified multimodal architecture that generates audio and video jointly, so sound and picture are aligned from the start rather than dubbed on afterwards — and stay aligned through extension rounds.

5

What is the clay-render reference in Seedance 2.5?

A textureless 3D model you supply to define spatial structure, character poses, motion paths and camera angles. Seedance 2.5 reads that blockout and renders realistic light direction, colour temperature, intensity and shadow on top of it.

6

Does Seedance 2.5 support 4K?

The official Seedance 2.5 launch post states no resolution. Native 4K with 10-bit colour was announced as a Seedance 2.0 upgrade, so treat 4K as a 2.0 spec until ByteDance publishes 2.5 resolution details.

7

When can I use Seedance 2.5 on this page?

As soon as our upstream provider opens the Seedance 2.5 route — ByteDance still lists API access as rolling out. The generator above runs Seedance 2.0, Fast and Mini meanwhile, and Seedance 2.5 appears in the model list the day it's available.

Start Building Your Seedance Workflow

Prompts, references and shot language transfer straight to Seedance 2.5. Build them now with Seedance 2.0 — free credits on signup.

Seedance 2.5 AI Video Generator — Features, vs 2.0 & Access