Wan 3.0 Pro text-to-video renders a written prompt at 1080p, 2K or 4K for 2 to 30 seconds, with audio in the same file. The 2K and 4K tiers are enlarged from a native 1080p Wan 3.0 render, and prompt expansion is on by default.
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
runway-fence-couple Written from nothing, with sound rendered into the same file — useful here because the event has a noise and a visible cause that must arrive together. The brief is built around one external force acting on fabric, which is a cleaner way to direct clothing than describing how it should sit. `resolution` starts at `1080p` on this endpoint and reaches `4k`, and `duration_seconds` runs to thirty.
- 1080p
- 9:16
- 2s
- Output5s
perfume-window-turn The prompt behind the clip on this page, run on the Wan 3.0 line at five seconds and 1080p with audio on.
- 1080p
- 16:9
- audio
- Output5s
monochrome-wind-machine The only monochrome request on this page, and the one that leans hardest on a single hard key against a black void. Three metres of chiffon in a wind machine is the stress test: it has to crack like a sail and twist around the shoulder without dissolving into mush. The clip shown was produced on the Wan 3.0 line as a style reference.
- 1080p
- 16:9
- audio
- Output5s
tattoo-parlour The second clip on this page. Candles and one desk lamp, a fine outline being shaded across ribs — the frame type the higher tier is actually for.
- 1080p
- 16:9
- audio
This example starts at $0.144 per output second. The Playground updates the estimate when you change the settings.