Why choose it
- 2–30 second one-pass generation
- Animate, first/last, and up to ten references
- Optional native audio
Original model creator
Alibaba
Wan 3.0
A longer 1080p one-pass text-and-image model with optional native audio, first/last frames, and up to ten references.
Official sampleSourced output
Official sample · Results vary by prompt and settings
Inspect the sample frame.
Direct answer
When should you use Wan 3.0?
Wan 3.0 is the Video Lab choice for longer one-pass shots that still need image control. Generate 2–30 seconds from text, animate a starting image, define first and last frames, or guide identity with up to ten references while keeping optional native audio, seed, and prompt enhancement.
Best for
Longer 1080p campaign and social shots that need image direction and optional sound in one pass.
Technical readout
The supported shot envelope.
- Duration
- 2–30 seconds
- Resolution
- 480p, 720p, or 1080p
- Aspect ratio
- Landscape, portrait, square, and social formats
- Audio
- Optional native audio
What to consider
- Negative prompt and multi-shot controls are not available
- Reference mode is capped at ten images in Video Lab
Prompt direction
How to prompt Wan 3.0
Describe a single continuous action for the full duration, then reuse a seed when you need prompt variations without changing the visual direction.
Start a Wan 3.0 promptQuestions, answered
Wan 3.0 FAQ
What is Wan 3.0 best for?
Wan 3.0 is best for longer one-pass clips at 480p–1080p, especially when you want optional native audio plus image animation, first/last frames, or references.
Which image workflows does Wan 3.0 support?
Video Lab supports single-image animation, first-to-last-frame direction, and up to ten reference images with Wan 3.0.
How long and at what resolution can Wan 3.0 generate?
Wan 3.0 generates 2–30 seconds in one pass at 480p, 720p, or 1080p.
Change the lens
Compare Wan 3.0 with another model.
Official sampleAlibabaOriginal model creatorHappy Horse 1.0
A native-audio text-and-image model with source-image animation, multi-image references, and broad social formats.See model
Official sampleAlibabaOriginal model creatorWan 2.7
A practical text-and-image generator with first/last frames, multi-image references, 1080p, and repeatable controls.See model
Official sample
GoogleOriginal model creatorVeo 3.1
A premium text-and-image video model for cinematic shots, guided frames, references, optional audio, and up to 4K output.See modelAlibaba lens selected
Direct your first Wan 3.0 shot.
Write the prompt, choose supported controls, and see the exact credit quote before you generate.
Open Wan 3.0 in Video Lab