Skip to main content

← All Models

Wan

One continuous scene, start to finish.

#LongTakes#1080p#References

Wan 3.0 from Alibaba leads the Artificial Analysis text-to-video leaderboard. It renders up to 30 seconds in a single take at 480p, 720p or 1080p, with a native audio track. Guide it with a first and last frame, or with up to 10 reference images plus reference video and audio. Wan 3.0 Prime is the same model, rendered faster.

Generate with Wan →

From 80 credits · Usually 3–6 minutes

Use Cases

Long Takes
1080p Scenes
Consistent Characters
Native Audio

Who it's for

Short-film Maker

Wants a 30-second scene without stitching clips.

E-commerce Brand

Keeps the product identical across every shot with reference images.

Social Creator

Needs Full HD clips with sound, ready to post.

What it's best for

✓Continuous scenes up to 30 seconds
✓Full HD output with a native soundtrack
✓Keeping characters and products consistent with reference images
✓Following the motion of a reference clip

Tutorial

🎬

Video tutorial coming soon

Specs & Pricing

Version · Resolution6s10s15s20s30sReference video
Wan 3.0 · 480p80 cr160 cr240 cr320 cr480 cr+240 cr
Wan 3.0 · 720p180 cr320 cr480 cr640 cr960 cr+480 cr
Wan 3.0 · 1080p380 cr640 cr960 cr1280 cr1920 cr+960 cr
Wan 3.0 Prime · 480p140 cr240 cr360 cr480 cr720 cr+360 cr
Wan 3.0 Prime · 720p300 cr500 cr740 cr1000 cr1500 cr+740 cr
Wan 3.0 Prime · 1080p600 cr1000 cr1500 cr2000 cr3020 cr+1500 cr

Prime renders faster at about 1.5× the price. With a reference video the clip can be up to 15 seconds, and the surcharge in the last column is added. A first/last frame and reference media are separate modes.

Ready to create?

From 80 credits · Usually 3–6 minutes

No subscription required — pay only for what you create.

Generate with Wan →