# Tencent-Hunyuan/HY-Motion-1.0

HY-Motion model for 3D human motion or 3D character animation generation.

Repository: https://github.com/Tencent-Hunyuan/HY-Motion-1.0
Canonical: https://ross.abutalabs.com/products/hy-motion-10
Homepage: https://hunyuan.tencent.com/motion
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-07-18T15:13:36+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 17
- inputs: {"age_days": 247, "days_push": 46, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2519, forks 210 (observed 2026-08-28T04:06:57.794505+00:00)

## What it is
HY-Motion 1.0 is a series of text-to-3D human motion generation models from Tencent Hunyuan, based on Diffusion Transformer and Flow Matching, scaled to billion parameters. It generates skeleton-based 3D character animations from text prompts for integration into 3D animation pipelines.

## Use cases
- generate 3d character animations from text prompts
- create skeleton-based human motion from a description
- text to motion generation for game animation
- produce 3d motion clips for animation pipelines
- evaluate semantic alignment of generated motion videos
- billion-parameter text-to-motion model inference

## When to choose
- you need state-of-the-art text-to-3D-motion generation with strong instruction following
- you want skeleton animations that plug into existing 3D animation pipelines
- you need an open-source DiT-based motion model with pretrained weights

## When to avoid
- you need video or image-to-motion generation rather than text-to-motion
- you lack a GPU or cannot run billion-parameter model inference locally
- you need a permissive license - the license is custom (NOASSERTION)

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, deep-learning, simulation
- platform: python
- tags: text-to-motion, 3d-animation, diffusion-transformer, flow-matching, motion-generation, character-animation, hunyuan, game-development, gpu, linux

## Member repositories
- Tencent-Hunyuan/HY-Motion-1.0 (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:57.794505+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 2026-08-30T02:26:06.553135+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/HY-Motion-1.0 (fetched 2026-08-28T04:06:57.794505+00:00, sha afc50e2b0ce1)
  - homepage: https://hunyuan.tencent.com/motion (fetched 2026-08-29T10:08:16.185010+00:00, sha e9ec7b1723ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.