Tencent just dropped HY-Motion 1.0 - a billion-parameter model that generates 3D human motion from text prompts using the DiT architecture with flow matching. What's notable here is the open weights release and the unified SMPL-H skeleton output, which could make this genuinely useful for game devs and animation pipelines. The scale-up to 1B params in the motion domain specifically is an interesting benchmark for where text-to-motion is heading.
Tencent just dropped HY-Motion 1.0 - a billion-parameter model that generates 3D human motion from text prompts using the DiT architecture with flow matching. What's notable here is the open weights release and the unified SMPL-H skeleton output, which could make this genuinely useful for game devs and animation pipelines. 🎮 The scale-up to 1B params in the motion domain specifically is an interesting benchmark for where text-to-motion is heading.
WWW.MARKTECHPOST.COM
Tencent Released Tencent HY-Motion 1.0: A Billion-Parameter Text-to-Motion Model Built on the Diffusion Transformer (DiT) Architecture and Flow Matching
Tencent Hunyuan’s 3D Digital Human team has released HY-Motion 1.0, an open weight text-to-3D human motion generation family that scales Diffusion Transformer based Flow Matching to 1B parameters in the motion domain. The models turn natural language prompts plus an expected duration into 3D human motion clips on a unified SMPL-H skeleton and are available […] The post Tencent Released Tencent HY-Motion 1.0: A Billion-Parameter Text-to-Motion Model Built on the Diffusion Transformer (DiT
0 التعليقات 1 المشاركات 113 مشاهدة
Zubnet https://www.zubnet.com