Motion study with audio
“An aerial shot follows a car along a coastal cliff road at golden hour, waves rolling in below, engine hum and wind.”
Wan AI · video model
WAN 3.0 PrimeGenerate AI video faster
from 6.8 credits / second · every plan · price breakdown · API playground
Made with WAN 3.0 Prime · Motion study with audio
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.
Original results
WAN 3.0 Prime examples made in Made
These examples use media produced for Made. Prompts are included when the production record allows them.
Image-to-video at 30 fps
“The bow draws across the strings, the spotlight flickering warm, a slow dolly toward the stage with resonant hall tone.”
Creative scene
“Autumn leaves swirl across a misty temple courtyard in morning light as the camera glides low over the stone.”
Scene brief
“Set the scene as a still before describing motion and sound.”
Start-frame control
“Use this image as the opening composition.”
Composition brief
“Establish framing and light, then hand the motion to the model.”
Where WAN 3.0 Prime fits best
Best uses
- Fast turnaround when someone is waiting on the clip
- Clips with synchronized audio, from quick cuts to 30 seconds
- 30 fps image-to-video with optional end-frame control
- Adaptive aspect ratio that follows the source image
Limits to know
- Prime costs about 40% more per second than standard WAN 3.0 for the same inputs; when nobody is waiting on the clip, standard is the better buy.
- The speed gap narrows at 1080p: 109 seconds against 143 for a 5-second clip in our test.
- Prompt expansion is enabled by default and can embellish terse prompts; write explicit motion language for exact control.
Specifications in Made
These are the controls exposed by Made, which may be narrower than a provider’s full API.
- Aspect ratios
- adaptive, 16:9, 4:3, 1:1, 3:4, 9:16
- Resolution
- 480p (default in Made), 720p, 1080p
- Duration
- 2–30 seconds
- Output formats
- MP4 with audio
- Reference images
- 2
- Processing
- Varies with duration and resolution; progress appears in the generation view.
How to use WAN 3.0 Prime in Made
- 1
Brief the scene and sound
Describe the subject, camera movement, pacing, and the ambient audio the clip should carry.
- 2
Anchor with a start image
Add a still for 30 fps image-to-video; adaptive aspect ratio follows the source automatically.
- 3
Set the duration
Pick a duration from 2 to 30 seconds and 480p, 720p, or 1080p; Made starts at 480p, the cheapest.
- 4
Review the take
Check motion, audio sync, and edges before downloading or refining the prompt.
Compare relevant models
video
WAN 2.2 Turbo
WAN 2.2 Turbo is Made’s fast iteration option for short text-to-video and image-to-video clips, with portrait and landscape output controls.
Explore model →video
Seedance 2.5
Seedance 2.5 is ByteDance’s newest video model in Made, generating clips up to 30 seconds in a single pass with native audio at 480p to 1080p — the longest single-shot ceiling in the Made library.
Explore model →agent
Made Auto
Upload an image or describe the result you need. Made Auto interprets the request, selects an available Made tool, and keeps follow-up edits in one conversation.
Explore model →Continue with a related tool
AI Video Generator
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.
Open tool →AI Image Generator
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.
Open tool →It is the faster version of Alibaba’s WAN 3.0 video model, with synchronized audio, up to 1080p output, and clips from 2 to 30 seconds.