ByteDance · Seedance 2.0
Seedance 2.0
Four modalities in, one multi-shot scene out.
What it is
Seedance 2.0 arrived in February 2026 as the first Seedance built on a unified multimodal audio-video joint-generation architecture. Text, image, audio and video can be mixed in a single request — up to nine images, three video clips and three audio clips — and referenced for composition, motion, camera language and sound.
Its 15-second multi-shot output and native two-channel audio moved AI video from a single clip to a scene. The reference-first way of directing that Seedance 2.5 extends to 30 seconds starts here.
Profiles describe the model, not a guarantee: the Skill folder is what makes the work repeatable, and the agent's settings decide what the model can reach.
What it's best at
The work this engine is built for, and where it earns its place in a run.
Multimodal reference
Text, images, video and audio in one request, including storyboards and camera language.
Multi-shot sequences
Fifteen seconds of connected shots from one prompt, rather than a single unbroken moment.
Physical motion
Complex interactions and multiple subjects held together with stable motion.
Native stereo audio
Music, ambience and voice generated alongside the picture.
A good first run
Three video Skills to try on Seedance 2.0 — each one a folder of instructions the model can pick up straight away.
Other models
The rest of the engine room.
ByteDance · Seedance 2.5
Seedance 2.5
ByteDance's latest video model: a 30-second audio-video scene from one pass, with up to 50 references.
- Duration
- 30s, extendable
- References
- 50 assets
Kuaishou · Kling 4.0
Kling 4.0
Kuaishou's production-grade model: 30-second takes, 10-bit HDR, omni-reference and precise keyframes.
- Duration
- 30s
- Output
- 4K HDR
Alibaba · Wan 3.0
Wan 3.0
Alibaba's all-in-one video model: 30 seconds, native sound, and references that include documents and web pages.
- Duration
- 30s at 30fps
- References
- Up to 20 assets
Ready to extend your agent?
Connect once, then install any Skill from our studio straight from your agent.