Alibaba · Wan 3.0
Wan 3.0
From a document to a 30-second film.
What it is
Wan 3.0 is Alibaba's all-in-one video model. One endpoint covers text-to-video, first and last-frame generation, multimodal reference, editing and extension — up to 30 seconds at 30fps, with native dialogue, BGM and sound effects.
What sets it apart is what it can read. Alongside up to ten images, five video clips and five audio clips, Wan 3.0 accepts documents and public web pages, turning a brief, a deck or a product page into video without a script intermediary.
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.
Documents and web pages
Reads a brief, presentation, spreadsheet or public URL as the source material.
30-second narratives
Multi-shot storytelling with synchronized dialogue, music and sound effects.
First and last frame
Pin the opening and closing frames; the model builds the motion between them.
Edit and extend
Add, remove or restyle elements, then continue the shot forward, backward or both ways.
A good first run
Three video Skills to try on Wan 3.0 — 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
ByteDance · Seedance 2.0
Seedance 2.0
ByteDance's unified audio-video model: text, image, audio and video references for 15-second multi-shot sequences.
- Duration
- 15s, multi-shot
- References
- 15 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
Ready to extend your agent?
Connect once, then install any Skill from our studio straight from your agent.