Motion Video Pose-Guided Animation
Motion Video generates character animation from a single reference image using pose guidance, with 14B and 1.3B model sizes for quality or speed.
- each::labs
- 2 variants
- Price
- See price
- Speed
- See speed
- Best for
- Image to Video
- Price
- See price
- Speed
- See speed
- Best for
- Image to Video
More from each::labs.
A family groups the versions of one model line. Open one to compare its variants side by side.
Working with Motion Video.
Motion Video is a pose-guided animation family: from one reference image it generates character motion without requiring the source and target to be aligned, which is what lets it work across different styles and environments. Two model sizes cover the quality-versus-cost decision.
When to choose Motion Video
Choose Motion Video when you have a single character image and want it animated by pose rather than by prompt. Kling Motion Control and Wan 2.2 Animate are the alternatives when you have a reference video to transfer from.
Choosing between the variants
The 14B model is the higher-quality tier for smoother, more detailed motion. The 1.3B model is markedly cheaper and faster, which suits drafts and high-volume runs.
Questions about Motion Video
The short answers. For anything specific to your setup, talk to our team.
Talk to an engineerPlan for your expected volume.The reference image does not have to match the target pose or framing, so a character can be animated without preparing an aligned source.
One. A single reference image is enough to generate the character's motion.
1.3B while you are testing, because it returns faster and cheaper; move to 14B for the take you intend to keep.