Seedance 2.5
30-second native 4K video from up to 50 reference inputs — announced, not yet on our API
No credit card required · 10 free credits to start
What is Seedance 2.5?
ByteDance's newest video model, announced on 23 June 2026 at the Volcano Engine FORCE conference in Beijing. Seedance 2.5 generates up to 30 seconds of native 4K video from a single prompt, accepts up to 50 multimodal reference inputs, and processes audio in the same latent space as the picture so sound lands on the action rather than being layered over it afterwards. ByteDance skipped 2.1 through 2.4 to mark it as a generational step rather than a point release. It is in enterprise beta with a public launch through ByteDance's own apps, and is not available through MotionArt yet — the moment an API endpoint exists, this page becomes a working generator. Until then, Seedance 2.0 is the newest Seedance you can run here.
What Seedance 2.5 does well
30 seconds in one generation
A single prompt produces up to 30 seconds, where most models cap out between 5 and 10. That is the difference between a shot and a scene — a full short-form beat without stitching clips together.
Native 4K, not upscaled
Output is generated at 4K rather than rendered small and enlarged afterwards, with 10-bit colour depth for smoother gradients in skies, skin and shadow.
Up to 50 reference inputs
Images, audio clips, 3D white models and style references can all be fed in together — up from 12 on Seedance 2.0. Enough to pin down a character, a set and a look at the same time.
Audio in the same latent space
Sound is generated jointly with the picture rather than matched to it afterwards, so a footstep lands on the footfall. This is the change with the largest effect on whether a clip is usable without an edit pass.
3D white-box preview
A low-fidelity animation can be previewed before committing to a full render, so blocking and camera moves are checked cheaply.
Around 20% better prompt adherence
ByteDance's own figure against Seedance 2.0. In practice it means fewer runs spent fighting a prompt the model half-followed.
Where Seedance 2.5 shines
Short-form ads end to end
Thirty seconds at 4K with synchronised audio covers a complete ad without an edit timeline — a script in, a deliverable out.
Character-consistent series
Fifty reference inputs is enough to hold one character, wardrobe and location steady across a run of clips instead of re-rolling until they match.
Pre-visualisation for production
The 3D white-box preview blocks out camera moves and staging before anyone commits budget to a shoot or a full render.
Questions about Seedance 2.5
What generating with Seedance 2.5 costs
Every model draws from the same credit balance. The plans below are the whole price list; the exact credit cost of a run is shown in the composer before you generate.
Prices in USD as of September 29, 2026. Unused monthly credits roll over and every plan can be cancelled at any time. Compare the plans in full.
More Seedance models
Other models in the Seedance family — or view all Seedance models.

Seedance 2.0 Fast Image to Video
ByteDance's most advanced image-to-video model, fast tier

Seedance 2.0 Fast Reference to Video
ByteDance's most advanced reference-to-video model, fast tier

Seedance 2.0 Text to Video
ByteDance's most advanced text-to-video model

Seedance 2.0 Image to Video
ByteDance's most advanced image-to-video model

Seedance 2.0 Reference to Video
ByteDance's most advanced reference-to-video model

Seedance 2.0 Fast Text to Video
ByteDance's most advanced text-to-video model, fast tier

Seedance 2.0 Mini Text to Video
Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.

Seedance 2.0 Mini Image to Video
Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.

Seedance 2.0 Mini Reference to Video
Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.

Seedance 1.5 Pro Text to Video
Generate videos with audio with Seedance 1.5

Seedance 1.5 Pro Image to Video
Generate videos with audio with Seedance 1.5 (supports start & end frame)

Seedance 1.0 Pro Text to Video
Seedance 1.0 Pro, a high quality video generation model developed by Bytedance.

Seedance 1.0 Pro Image to Video
Seedance 1.0 Pro, a high quality video generation model developed by Bytedance.

Seedance 1.0 Pro Fast Text to Video
Text to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost

Seedance 1.0 Pro Fast Image to Video
Image to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost
Explore other model families
Compare Seedance 2.5 with the rest of the line-up, or browse the full model directory.
Start generating for free
10 free credits, no credit card. Pick Seedance 2.5 in the composer and generate your first image.