AI Models
What each model is good at, where it differs from the others, and what it costs to run.
Kuaishou's Kling 2.6 motion transfer. One picture of a subject plus one clip whose motion it copies. A prompt is optional.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Kling 2.6 Motion Control is Kuaishou's motion-transfer model on the Kling 2.6 line. It does not start from a prompt alone. It needs a person or subject, and a clip that already moves the way you want.
Kuaishou describes motion control as transferring the full-body motion of a reference clip onto a character image, including lip-sync and facial expression from that clip. The picture supplies who it is. The clip supplies how they move.
Attach one picture of the subject and one clip. A prompt is optional. There is no sound switch to set. The motion comes from the clip.
Kling 3.0 Motion Control is the same job on the Kling 3.0 line. Kling 2.6 makes a clip from a prompt or one opening picture and does not copy a performance. Kling 3.0 Omni can restyle a clip, which is a different job from copying its motion onto a new subject.
Yes. One picture of the subject, one clip of the motion.
No. Add one if you need to say what else should change. The motion still comes from the clip.
No. Text-to-video is Kling 2.6, not this model.
It is the motion-control model on the newer Kling line. The inputs are the same: one picture, one clip, optional prompt.
