HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation

TL;DR

HY-Motion 1.0 is a large-scale, diffusion transformer-based model that generates diverse 3D human motions from text, achieving state-of-the-art performance through extensive training and data processing.

Contribution

First to scale diffusion transformer flow matching models to billion-parameter size for text-to-motion generation, with a comprehensive training pipeline and extensive motion coverage.

Findings

Outperforms existing open-source benchmarks in instruction-following accuracy.

Generates over 200 motion categories across 6 major classes.

Achieves high-quality, diverse 3D human motions from textual descriptions.

Abstract

We present HY-Motion 1.0, a series of state-of-the-art, large-scale, motion generation models capable of generating 3D human motions from textual descriptions. HY-Motion 1.0 represents the first successful attempt to scale up Diffusion Transformer (DiT)-based flow matching models to the billion-parameter scale within the motion generation domain, delivering instruction-following capabilities that significantly outperform current open-source benchmarks. Uniquely, we introduce a comprehensive, full-stage training paradigm -- including large-scale pretraining on over 3,000 hours of motion data, high-quality fine-tuning on 400 hours of curated data, and reinforcement learning from both human feedback and reward models -- to ensure precise alignment with the text instruction and high motion quality. This framework is supported by our meticulous data processing pipeline, which performs rigorous motion cleaning and captioning. Consequently, our model achieves the most extensive coverage, spanning over 200 motion categories across 6 major classes. We release HY-Motion 1.0 to the open-source community to foster future research and accelerate the transition of 3D human motion generation models towards commercial maturity.