body-models 0.13.3

Multi-backend parametric body models (SMPL, SMPLH, SMPLX, FLAME, SKEL, ANNY, MHR, SOMA, GarmentMeasurements, BrainCo, G1) for NumPy, PyTorch, and JAX

body-models

body-models provides a shared interface for parametric human body, head, hand, anatomical, measurement, and robot models across NumPy, PyTorch, and JAX.

Documentation: https://abcamiletto.github.io/body-models/

Features

• Shared API across human, anatomical, hand, head, measurement, and robot models
• NumPy, PyTorch, and JAX backends
• Separate mesh and skeleton forwards with forward_vertices() and forward_skeleton()
• Prepared identities for repeated poses with fixed shape/expression parameters
• Skinned-mesh and rigid-body helpers for viser
• Mesh simplification and vertex-subset forwards for supported mesh models
• Multiple rotation representations for supported pose models

Install

uv add body-models

Install optional extras when needed:

uv add "body-models[torch]"
uv add "body-models[jax]"
uv add "body-models[viser]"

Quick Start

from body_models.smpl.torch import SMPL

model = SMPL(gender="neutral")
params = model.get_rest_pose(batch_dims=(1,))

vertices = model.forward_vertices(**params)
skeleton = model.forward_skeleton(**params)

When shape-dependent identity parameters stay fixed across many poses, prepare them once and pass the returned dictionary back through identity. This avoids recomputing rest joints, local offsets, and rest vertices on every forward pass.

shape = params.pop("shape")
identity = model.prepare_identity(shape)

vertices = model.forward_vertices(**params, identity=identity)
skeleton = model.forward_skeleton(**params, identity=identity)

For models with expression-dependent rest state, such as SMPL-X and FLAME, pass both identity controls to prepare_identity(shape, expression). Skeleton-only work can use skip_vertices=True to avoid preparing rest vertices.

Supported Models

• Full bodies: SMPL, SMPL-H, SMPL-X, ANNY, MHR, SOMA, GarmentMeasurements
• Anatomicals: SKEL, MyoFullBody
• Heads: FLAME
• Hands: MANO
• Robots: BrainCo, G1

See the model docs for setup, supported backends, inputs, and model-specific behavior.

Extras

Optional integrations live under body_models.extras, including the viser plugin.

import viser
from body_models.extras import viser_plugin as vp
from body_models.smpl.numpy import SMPL

server = viser.ViserServer()
model = SMPL(gender="neutral")
handle = vp.add_body_model(server.scene, "/body", model)
handle.set_pose(**model.get_rest_pose())

Development

uv run ruff format .
uv run ruff check .
uv run ty check

License

See the documentation and upstream model projects for model-specific license terms.