Wan 3.0 Pro Prime text-to-video renders a written prompt at 1080p, 2K or 4K for 2 to 30 seconds, with audio included. The 2K and 4K tiers are enlarged from a native 1080p Wan 3.0 Prime render.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
crypt-candelabra The clip this page opens on. A third of the brief is spent on framing alone — whole head in shot, headroom above the hair, cut at the waist — because the usual failure in a close-up like this is the model cropping the face out of its own frame. Candlelight is the only key and the audio arrives in the same pass. Produced on the Wan 3.0 line as a style reference.
- 16:9
- audio
- 5s
- Output5s
underwater-silk-descent Weightless motion with no ground to reference: a crimson gown blooming and twisting as she sinks, hair fanning, bubbles trailing from her fingertips, and a camera that arcs and tilts at the same time. Nothing in the frame is allowed to settle — which is exactly the kind of shot the higher tier is for. Produced on the Wan 3.0 line as a style reference.
- 16:9
- audio
- 5s
- Output5s
night-ferry The one two-person scene on this page. Handheld, available light, no resolution set so it takes the default — a deliberately plain request, kept here because the wording runs through unchanged where a lot of other models refuse it. Produced on the Wan 3.0 line as a style reference.
- 16:9
- audio
- 5s
This example starts at $0.234 per output second. The Playground updates the estimate when you change the settings.