Motion study
“A glassblower turns molten glass at the furnace mouth, heat shimmer rising, the camera arcing slowly from the flame to their focused face.”

Wan AI · video model
from 0.5 credits / second · every plan · price breakdown · API playground
Made with WAN 3.0 · Motion study
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.
Original results
These examples use media produced for Made. Prompts are included when the production record allows them.
“A glassblower turns molten glass at the furnace mouth, heat shimmer rising, the camera arcing slowly from the flame to their focused face.”
“Animate the scene: the glass glows and turns, sparks drift, furnace roar fills the room, the camera holds a slow arc.”
“Hot air balloons lift off over terraced fields at dawn, burners firing in turn, a slow aerial drift among the envelopes as mist burns off below.”

“Use this image as the opening composition.”

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

“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.
Write a prompt on its own, or add a start image — and optionally an end frame — to anchor the clip.
Durations run from 2 to 30 seconds; describe how the shot evolves over longer takes.
Pick a fixed aspect ratio, or adaptive to follow the input image’s shape.
Check motion stability across the take, then adjust one instruction at a time.
from 0.5 credits / 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 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
Seedance 2.0 Mini is the fast, low-cost tier of ByteDance’s Seedance 2.0 video model, generating 4 to 15 second clips at 480p or 720p with audio for quick drafts and high-volume runs.
Explore model →video
Happy Horse 1.1 is Alibaba’s flagship video model — a long-running #1 on the Artificial Analysis Video Arena — generating 3 to 15 second clips at 1080p with native audio and multilingual lip-sync.
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 Alibaba’s WAN 3.0 video model at its standard speed and price, with the same inputs and 30-second ceiling as WAN 3.0 Prime.