Motion study
“Handheld-style clip: a seaside carnival at dusk, the ferris wheel turning, crowds drifting past food stalls”
video model
Generate fast AI video drafts with WAN 2.2 5B
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.
$0.15 / video at provider cost for members — see the full price breakdown
What you need to start
Describe the shot and its motion — or add a start image to animate.
Loading...
Original results
WAN 2.2 5B examples made in Made
These examples use media produced for Made. Prompts are included when the production record allows them.
Image-to-video
“The puppy bounds through the grass toward camera, ears flopping, lens flaring”
Creative scene
“Syrup pours over a pancake stack in macro slow motion, butter sliding, warm diner light”
Start-frame control
“Use this image as the opening composition.”
Scene brief
“Set the scene as a still before describing its motion.”
Composition brief
“Plan the shot as a still, then hand the motion to the model.”
Where WAN 2.2 5B fits best
Best uses
- Cheap, fast drafts before committing to a premium model
- Flat per-video pricing that stays the same at any setting
- Animating a still image without a per-second meter
- Vertical, square, and widescreen previsualization
Limits to know
- No audio — clips render as silent MP4s; add sound in an editor or regenerate on an audio-native model.
- Clip length is fixed (81 frames at 24 fps, about 3 seconds) — there is no duration control in Made.
- Output tops out at 720p; treat results as drafts and upscale or re-shoot hero clips on a larger model.
Specifications in Made
These are the controls exposed by Made, which may be narrower than a provider’s full API.
- Aspect ratios
- 16:9, 9:16, 1:1
- Resolution
- 580p, 720p (default in Made)
- Duration
- Fixed clip length — 81 frames at 24 fps, about 3 seconds
- Output formats
- MP4 (no audio)
- Reference images
- 1
- Processing
- One of the fastest video models in the library; progress appears in the generation view.
How to use WAN 2.2 5B in Made
- 1
Write the shot
Describe the subject, motion, and camera path — keep it visual; the model does not generate sound.
- 2
Add a start image if needed
Upload a still to animate; WAN 2.2 5B keeps its composition and adds motion.
- 3
Choose the format
Pick 16:9, 9:16, or 1:1 and 580p or 720p — the flat price is the same either way.
- 4
Iterate freely
Flat per-video pricing makes rapid retries cheap; refine one instruction at a time, then re-shoot the keeper on a premium model.
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
WAN 2.7
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.
Explore model →video
LTX-2.5 Fast
LTX-2.5 Fast is Lightricks’ open audio-video model, generating 6 to 20 second clips with native synchronized audio included at every resolution, from text or a start image.
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 compact 5-billion-parameter member of Wan AI’s 2.2 family, built for fast, low-cost video drafts from text or a start image.