Views
No views yet
1from motius import Pipeline
2
3pipe = Pipeline.from_pretrained(
4 "ZeyuLing/Motius-HYMotion-G1",
5 device="cuda",
6)
7result = pipe.infer_text_to_motion(
8 "a robot walks forward and waves",
9 num_frames=180,
10)
11g1_38 = result["g1_38"]
12qpos_36 = result["g1_qpos"]g1_38 at 30 fps. The g1_qpos decode is
exact and does not pass through SMPL or inverse kinematics. See the
Motius Model Card
for training, representation, and benchmark details.