Prompt
Text · Required
Loading the current model…
We could not open this model.
Return to the catalogue and choose an available model.
Back to the catalogue
- Alibaba
- Standard
- Generate video
Wan 3.0
Direct next-generation multimodal video with native audiovisual control.
Compare Wan 3.0 settings and cost estimates. Wan scenes with optional generated audio, a first frame, and a video reference, including flexible portrait and landscape work.
- Generate video
Wan 3.0 pricing example
$0.0921 Estimated per run
- Aspect ratio: auto
- Resolution: 480p
- Duration: 2
- With audio: false
Estimate checked . This example uses the configuration shown above. Inputs and settings can change the price; check the estimate for your own run before generating. Project storage is billed separately.
How AI usage and project pricing work →Curated output references.
What goes in. What comes back.
The model defines every slot it reads and every result it returns. Required inputs must be present before a run can begin.
Prompts and source material
First frame
Image and Video · Optional
Last frame
Image and Video · Optional
Video reference
Video · Optional
Files and structured results
Video
Video
Configure the run.
| Control | Available values | Requirement |
|---|---|---|
| Aspect ratio | auto, 16:9, 4:3, 1:1, 3:4, and 9:16 | Optional |
| Resolution | 480p, 720p, and 1080p | Optional |
| Duration | 2–15 | Optional |
| With audio | On, Off | Optional |
| Seed | Integer | Optional |
Works especially well for
- Wan scenes with optional audio, a first frame, and a video reference, including flexible portrait and landscape work.
Know the trade-offs
- Although the vendor describes longer generation and many input types, LatestEffects configures 2–15 seconds at 480p/720p/1080p and no document or audio-reference input.
Continue from the result
Use it inside a production
- Suggested exercise: direct a fifteen-second product reveal with one stable subject, a gradual camera move, and a separately described ambient soundtrack. →
- Choose Seedance 2.5 if a continuous take must exceed fifteen seconds in this app; choose Wan 2.7 R2V when multiple still references are essential. →
Compare similar models
Compare models for the same capability. Check their inputs, output settings, and estimate using the same brief.
Configure the model.
Keep the result in the cut.
The generation returns to the scene, asset folder and timeline it belongs to.