Skip to main content

A parametric body model based on MakeHuman for PyTorch.

Project description

Anny Body

Anny

Anny is a differentiable human body mesh model written in PyTorch. Anny models a large variety of human body shapes, from infants to elders, using a common topology and parameter space.

ArXiv Demo Blogpost

Features

  • Anny is based on the tremendous work of the MakeHuman community, which offers plenty of opportunities for extensions.
  • We provide both full body and part-specific models for hands and faces.
  • Anny is open-source and free.

News

  • 2025-11-21: support for different mesh topologies.
  • 2025-11-05: initial release.

Installation

Full installation (depends on warp-lang, which may require some manual work to install):

pip install anny[warp,examples]

Minimal dependency installation (will use more memory with large batch sizes):

pip install anny

Installation from latest sources:

pip install anny[warp,examples]@git+https://github.com/naver/anny.git

Tutorials

To get started with Anny, you can have a look at the different notebooks in the tutorials repository:

Interactive demo

We provide a simple Gradio demo enabling to interact with the model easily:

python -m anny.examples.interactive_demo
Interactive demo

License

The code of Anny, Copyright (c) 2025 NAVER Corp., is licensed under the Apache License, Version 2.0 (see LICENSE).

data/mpfb2: Anny relies on MakeHuman assets adapted from MPFB2 that are licensed under the CC0 1.0 Universal License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

anny-0.2.0.tar.gz (42.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

anny-0.2.0-py3-none-any.whl (42.6 MB view details)

Uploaded Python 3

File details

Details for the file anny-0.2.0.tar.gz.

File metadata

  • Download URL: anny-0.2.0.tar.gz
  • Upload date:
  • Size: 42.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for anny-0.2.0.tar.gz
Algorithm Hash digest
SHA256 fce073cb999e7fa591c15e8310b6840544cf62f79c063ac39cde0132ce67e82d
MD5 295fa4759e5580f9d38771426b67bc59
BLAKE2b-256 9f91615ed550afb16182c543ae166c412dd83c92b9c9081d97e61ea525eac037

See more details on using hashes here.

File details

Details for the file anny-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: anny-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 42.6 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for anny-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b8ecf12b7fad4458d2016fb109c4ccb9672f799c2f003a2a054a1fc6fe04b3bf
MD5 0363d4680ba97382d36a8b53baaebd33
BLAKE2b-256 4bac0d13f24b8007393c74c8195589c0c8817d7915defaa30b844e94ddf4fc49

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page