Its licence excludes the UK and EU, which rules out British game developers and animators despite the free weights.
Kenning's take
What it does
HY-Motion 1.0 generates 3D human motion, such as walking or dancing, from a text prompt as skeleton-based animation that drops into standard 3D pipelines. Tencent says it is the first text-to-motion model of this kind scaled to about a billion parameters, with a 0.46B Lite version. Weights and code are on Hugging Face and GitHub, with a demo on Hugging Face Spaces.
- Text to 3D character animation
- 1.0B and 0.46B Lite models
- Skeleton output for animation pipelines
- Trained on 3,000+ hours of motion data
- Hugging Face demo
Who it suits. Game developers and 3D animators who want quick motion drafts.
Key facts
- Category
- AI models
- Made by
- Tencent
- Based in
- China
- Released
- 30 December 2025
- How to get it
- open weights on Hugging Face, code on GitHub, demo on Hugging Face Spaces; Tencent's licence states it does not apply in the UK, EU or South Korea
- Works on
- open-weights, Web
- In the UK
- No
- Free plan
- yes, open weights (outside the UK, EU and South Korea)
FAQ
When was HY-Motion 1.0 released?
Tencent released it on 30 December 2025.
How much memory does HY-Motion need?
Tencent lists a minimum of 26GB of GPU memory for the standard 1.0B model.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.
AlphaGenome Atlas
Google DeepMind database of AI-predicted effects for every possible single-letter change in human DNA.
Amazon Nova 2
Amazon's second family of Nova AI models, covering reasoning, speech conversation and combined text-and-image generation.
Cisco Antares
Cisco's small open-weight models that find where known security vulnerabilities sit in a codebase, running locally.