%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Recently, Tencent Hunyuan officially released and open-sourced its new text-to-3D motion large model — HY-Motion 1.0. With a ten-billion parameter scale and an architecture based on Diffusion Transformer (DiT), this model marks a major breakthrough in the field of 3D character animation generation. HY-Motion 1.0 aims to provide high-quality, standardized skeletal animations, helping game developers, animators, and researchers improve their creative efficiency and lower the barriers to 3D animation production, allowing more individual creators to realize their ideas.
In the process of creating 3D character animations, the lack of high-quality action assets has long been a pain point in the industry, leading to high costs and long production cycles. The release of HY-Motion 1.0 is aimed at solving this issue. The model can generate smooth and coherent actions, especially excelling in handling complex temporal logic and fine-grained limb control. The generated animations can accurately respond to user text descriptions, providing high-quality asset prototypes for post-production and effectively reducing the cost of manual adjustments.
HY-Motion 1.0 has a wide range of applications, covering basic movements, daily life, social leisure, fitness outdoor, sports competitions, and character actions for games, with over 200 action categories, truly achieving "ready to use out of the box." At the same time, the model's output can be seamlessly integrated into existing production pipelines, such as Unreal Engine, Unity, Maya, and Blender, supporting standardized skeletal animation exports, making it easy for developers to apply it to any 3D character.
On the technical level, HY-Motion 1.0 significantly improves generation quality and generalization ability through a ten-billion parameter model and a multi-source data foundation. Its full-stage training system ensures that the generated actions are reasonable and precise, and the built-in "intelligent motion director" function can transform vague user descriptions into structured instructions, achieving a deep understanding of creative intent.
Tencent Hunyuan stated that it will continue to enhance HY-Motion 1.0's capabilities in action quality, semantic understanding, and long-sequence generation to promote the advancement of 3D character animation production technology.
【Experience Address】
🌐 Project Homepage: https://hunyuan.tencent.com/motion
🔗 Github: https://github.com/Tencent-Hunyuan/HY-Motion-1.0
🤗 Hugging Face: https://huggingface.co/tencent/HY-Motion-1.0
📄 Technical Report: https://arxiv.org/pdf/2512.23464