Motion study
“Cinematic clip: wild horses gallop through shallow tide water under a storm sky, spray freezing in backlight”

Wan AI · video model
from 1 credit / second · every plan · price breakdown · API playground
Made with WAN 2.7 · Motion study
WAN 2.7 is Wan AI’s current-generation video model, generating 2 to 15 second clips at up to 1080p with synchronized audio from a text prompt or a start image.
Original results
These examples use media produced for Made. Prompts are included when the production record allows them.
“Cinematic clip: wild horses gallop through shallow tide water under a storm sky, spray freezing in backlight”
“The brush completes a sweeping character in one take, ink bleeding into the paper fibers, macro camera”
“Cinematic clip: a ramen chef torches chashu in a dark counter bar, flames flaring, smoke curling into the spotlight”

“Use this image as the opening composition.”

“Set the scene as a still before describing its motion and sound.”

“Plan the shot as a still, then hand the motion to the model.”
These are the controls exposed by Made, which may be narrower than a provider’s full API.
Describe the subject, motion, camera path, and the audio the clip should carry — sound is generated with the picture.
Upload a still to animate; WAN 2.7 keeps its composition, which is also how you control framing.
Pick any duration from 2 to 15 seconds and 720p or 1080p.
Check motion, audio, and continuity, then adjust one instruction at a time.
from 1 credit / second — the full breakdown, verified.
6 tested prompts with the outputs they produced.
Side-by-side prices and specs, with a straight verdict.
Side-by-side prices and specs, with a straight verdict.
Side-by-side prices and specs, with a straight verdict.
Side-by-side prices and specs, with a straight verdict.
Side-by-side prices and specs, with a straight verdict.
Side-by-side prices and specs, with a straight verdict.
video
WAN 3.0 is Alibaba’s WAN 3.0 video model at its standard speed and price, generating 2 to 30 second clips at up to 1080p with audio included. WAN 3.0 Prime runs the same inputs faster for about 40% more per second.
Explore model →video
WAN 3.0 Prime is the faster way to run Alibaba’s WAN 3.0, with the same inputs: clips from 2 to 30 seconds with synchronized audio at up to 1080p. In our test it finished a 5-second 720p clip in 83 seconds, against 143 on standard WAN 3.0.
Explore model →video
WAN 2.2 5B is Wan AI’s compact draft model, generating short clips from a text prompt or a start image at 580p or 720p in three aspect ratios — billed at a flat rate per video, not per second.
Explore model →Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality.
See the tool →Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.
See the tool →It is Wan AI’s current-generation video model, generating clips at up to 1080p with synchronized audio from text or a start image.