Broad duration range
Shape quick tests or longer scene motion within the mapped range.
Model guide
Wan 3.0 for longer, reference-led scenes.
A value-focused Labs route for continuous motion, image-guided scenes and native audio across flexible durations.
What it gives you
A practical route when the scene needs room to develop.
Wan 3.0 supports text, frames and multiple references across a broad duration range. Soho labels it Labs while visual-quality sampling continues, but its mapped customer transaction route is active.
Reference-led
Use frames or multiple images to establish the visual direction.
Value route
A practical option for iterations that still need native audio and continuity.
Model details
Wan 3.0
The latest standard Wan route: 2–30 second clips, up to ten image references, three resolution tiers and native audio. Available in Labs while Soho collects more visual-quality samples.
- Inputs
- Text · First frame · Last frame · Reference images
- Duration
- 2–30s
- Resolution
- 480p · 720p · 1080p
- Aspect ratios
- adaptive · 16:9 · 4:3 · 1:1 · 3:4 · 9:16
- Reference images
- Up to 10
- Native audio
- Yes
- Availability
- Labs
Generated examples
Generated examples
Real Soho Frame examples identified by the model used.
Vintage New York
Wan 3.0
After Midnight
Wan 3.0
A clear workflow
A clear workflow
- 01
Set the input
Choose text, frames or references from the inputs the model actually accepts.
- 02
Shape the output
Select duration, resolution, ratio and audio where those controls are available.
- 03
Review in the project
The result returns beside its source with the generation settings attached.
Questions
Questions
Why is Wan 3.0 labeled Labs?
Its customer transaction and storage route is active, while Soho continues expanding reviewed visual-quality samples.
How many references can I use?
The active catalog documents up to 10 reference images for the mapped reference mode.
Does it support first and last frames?
Yes. The mapped route supports first and last frames as well as reference-image mode.
Try it on your next shot.
Open Video with the model selected and keep the result in its project.
Create with this model