Video generation

Seedance 2.5

by ByteDance

ByteDance's next‑generation video model.
Up to 30s native clips, 50 references, native audio.

Seedance 2.5

Key features

A humpback whale glides past a free diver in clear blue waterStart creating

These are ByteDance's launch specs for Seedance 2.5; independent benchmarks are still to come.

Technical specifications

Rolling out

Enterprise beta live; no free quota at enablement.

Aug 7, 2026

Experience Center and API expected to be fully available.

Up to 30s

Single-shot native length, with the option to extend twice.

Up to 50

30 images, 10 video, and 10 audio inputs per generation.

10+ native

Native generation across 10+ languages.

3 modes

Text-to-video, image-to-video, and reference-to-video.

Use cases

Longer-form ad spots

A 30-second native clip covers a full broadcast spot in one generation, instead of cutting several shorter shots together.

Short drama and skits

Longer single takes suit short-form drama and serialized skits, where a scene needs room to breathe past a four-second beat.

Film and TV previz

Quick, longer previsualization for film and television, where a director wants a sequence to play out before a full shoot.

Reference-led continuity

Up to 50 references let a team lock a character, set, and palette across a sequence for tighter continuity.

Localized versions

Native support for 10+ languages aims at making the same scene with captions, voiceover, or titles in several languages.

Audio-driven scenes

A voice, music, or sound-effect track can drive pacing, beat-matching, and lip-sync through an audio-only reference.

Prompt examples

Long-form ad

A 30-second perfume spot, one unbroken push through a glass atrium at dusk

Edit prompt

Short drama

Two estranged sisters meet on a rain-soaked station platform at night

Edit prompt

Previz sequence

Heist crew crosses a moonlit rooftop, camera tracking low behind them

Edit prompt

Reference continuity

Same red-coated detective walks three different city streets, dusk to dark

Edit prompt

Localized title card

Mountain summit at sunrise with a clean lower-third title, multiple languages

Edit prompt

Slow-motion nature

A waterfall in slow motion, spray catching low golden light, ultra-detailed

Edit prompt

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$9/ month
billed as $0 per year

900 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3200 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6200 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$170/ month
billed as $0 per year

24000 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is Seedance 2.5?
Seedance 2.5 is ByteDance's next-generation video model. It generates up to 30 seconds of native single-shot video, accepts up to 50 multimodal references (30 images, 10 video, and 10 audio), and adds native audio with support for 10+ languages, building on the Seedance 2.0 line. ByteDance's Experience Center and API are expected to be fully available on August 7, 2026.
When does Seedance 2.5 come out?
ByteDance's Seedance 2.5 enterprise guide lists the Experience Center and the API as expected to be fully available on August 7, 2026, following an enterprise beta. There is no free quota; enabling the model needs an account balance above USD 30.1 or an active Seedance 2.0 resource package. The specs on this page are ByteDance's launch numbers; independent benchmarks are still to come.
How is Seedance 2.5 different from Seedance 2.0?
The headline change is length: up to 30 seconds of native single-shot video, versus the few-second clips typical today. Seedance 2.5 also takes far more references (up to 50: 30 images, 10 video clips, and 10 audio, against Seedance 2.0's 9 images and 3 audio/video clips), adds an audio-only reference for lip-sync and beat-matching, strengthens in-clip editing and extension, and adds native support for 10+ languages.
How long can Seedance 2.5 videos be?
Seedance 2.5 generates up to 30 seconds in a single native pass, up from 15 seconds on Seedance 2.0. That is a notable jump over most current models, which top out at a few seconds to roughly a dozen, and it covers full ad spots and short scenes in one generation. ByteDance also gives the option to extend a clip twice, so a scene can run longer without cutting separate shots together.
What resolution does Seedance 2.5 support?
ByteDance's Seedance 2.5 enterprise guide does not publish an output resolution. It documents reference inputs of up to 4K for images and 480p to 4K for video clips. We'll update this page with the output resolution once ByteDance confirms it at launch.
Will there be a Seedance 2.5 Pro or Turbo tier?
ByteDance has shipped tiers like Seedance 2.0 Fast and Seedance 2.0 Mini alongside its main models before, so Pro or Turbo style variants of Seedance 2.5 are likely to follow. We'll add them here once they're announced.

More about Seedance 2.5

Seedance 2.5: complete guide, features, prompts, and longer video

The complete Seedance 2.5 guide: longer single-take video, reference-led continuity, camera control, and native audio, with prompt examples.

Seedance 2.5 prompt library: cinematic video examples

A growing collection of Seedance 2.5 video prompts with example clips. Copy any prompt, generate it on Morphic, and learn the shot-brief patterns that work best with Seedance 2.5.

Other models

Kling 4.0

Kling

Kuaishou's next Kling flagship, expected soon. Longer clips and sharper detail are on the way.

MiniMax H3

MiniMax

MiniMax's multimodal video model. 2K, native stereo audio, clips up to 15s.

Flux 3

Black Forest Labs

Black Forest Labs' world model for image, video, and audio, with sound that matches the action.

Seedream 5.0 Pro

ByteDance

Grounded editing and multi-layer separation. Dense infographics and native text in 14 languages.