# GuyTevet/motion-diffusion-model

The official PyTorch implementation of the paper "Human Motion Diffusion Model"

Repository: https://github.com/GuyTevet/motion-diffusion-model
Canonical: https://ross.abutalabs.com/products/motion-diffusion-model
Language: Python
License: MIT
License Family: permissive
Last push: 2025-10-01T00:29:26+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 44, release rhythm 35, longevity 100
- inputs: {"age_days": 1434, "days_push": 337, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4092, forks 458 (observed 2026-08-28T04:08:34.618037+00:00)

## What it is
Official PyTorch implementation of the Human Motion Diffusion Model (MDM) paper, generating 3D human motion sequences from text prompts using diffusion models. Includes the faster DiP text-to-motion model and evaluation tooling on HumanML3D and KIT benchmarks.

## Use cases
- generate human motion animations from text descriptions
- text-to-motion synthesis for character animation
- research baseline for motion diffusion models
- evaluate motion generation on HumanML3D benchmark
- create skeletal animation clips from prompts

## When to choose
- you need a research-grade text-to-motion diffusion model in PyTorch
- you want to reproduce or extend the MDM paper
- you need fast motion generation with the DiP model

## When to avoid
- you need production-ready animation tooling for game engines
- you want a GUI-based animation editor rather than a research codebase
- you work outside Python/PyTorch environments

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing
- domain: machine-learning, deep-learning, computer-vision
- platform: python
- tags: diffusion-model, human-motion, text-to-motion, pytorch, motion-generation, research-code, character-animation, research, gpu

## Member repositories
- GuyTevet/motion-diffusion-model (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.618037+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:20.604728+00:00, confidence not recorded.
  - readme: https://github.com/GuyTevet/motion-diffusion-model (fetched 2026-08-28T04:08:34.618037+00:00, sha 7286e346f6c8)
- Data as of 2026-08-30T08:39:29.467469+00:00.