DreamActor V2 transfers motion from a driving video to characters in an image. Great performance for non-human and multiple characters. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.05per run·~20 / $1
DreamActor V2 is advanced motion transfer model that animates any character image using a driving video. Upload a portrait or character image and a reference video — the model makes your character perform the same movements, expressions, and gestures as the person in the driving video.
Motion transfer Transfer movements, expressions, and gestures from a driving video to any character image.
Any character Works with photos, illustrations, anime characters, or any portrait-style image.
Expression capture Accurately captures facial expressions, head movements, and body gestures.
Natural animation Generates smooth, realistic motion that matches the driving video timing.
Simple workflow Just two inputs — an image and a video — no complex setup required.
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Character image to animate (URL or upload) |
| video | Yes | Driving video with movements to transfer (URL or upload) |
| Video Duration | Cost |
|---|---|
| 1 second | $0.05 |
| 5 seconds | $0.25 |
| 10 seconds | $0.50 |
| 30 seconds | $1.50 |