ZeyuLing's picture
Add files using upload-large-folder tool
78fa5ce verified
|
Raw
History Blame Contribute Delete
818 Bytes
metadata
library_name: motius
pipeline_tag: text-to-motion
license: mit
tags:
  - human-motion
  - two-person-text-to-motion
  - intermask
  - interhuman

Motius InterMask InterHuman

Inference-only SafeTensors artifact for InterMask, adapted from the official MIT-licensed repository. The VQ-VAE and masked Transformer contain no optimizer or scheduler state.

from motius.pipelines.intermask import InterMaskPipeline

pipe = InterMaskPipeline.from_pretrained(
    "ZeyuLing/motius-intermask-interhuman",
    bundle_kwargs={"device": "cuda"},
)
motion = pipe("two people hug", motion_len=120, seed=42)
# (1, 120, 2, 262)

See the full Motius model card.