HY-Motion 1.0 opens a 1B text-to-motion model with a full RL loop
- Source
- x.com
- Date
✨We are excited to open-source Tencent HY-Motion 1.0, a billion-parameter text-to-motion model built on the Diffusion Transformer (DiT) architecture and flow matching. Tencent HY-Motion 1.0 empowers developers and individual creators alike by transforming natural language into high-fidelity, fluid, and diverse 3D character animations, delivering exceptional instruction-following capabilities across a broad range of categories. The generated 3D animation assets can be seamlessly integrated into typical 3D animation pipelines.🎮🎥 Highlights: 🔹Billion-Scale DiT: Successfully scaled flow-matching DiT to 1B+ parameters, setting a new ceiling for instruction-following capability and generated motion quality. 🔹Full-Stage Training Strategy: The industry’s first motion generation model featuring a complete Pre-training → SFT → RL loop to optimize physical plausibility and semantic accuracy. 🔹Comprehensive Category Coverage: Features 200+ motion categories across 6 major classes—the most comprehensive in the industry, curated via a meticulous data pipeline. 🌐Project Page: https://t.co/IIGGQj25Pg 🔗Github: https://t.co/L4642SrQoW 🤗Hugging Face: https://t.co/Gmgv0O0CKl 📄Technical…
Context
Tencent's HY-Motion 1.0 turns written descriptions into movement for a 3D character's skeleton. The output can enter an animation workflow as motion data, allowing creators to start from a requested action. The repository provides pretrained models and code.
The team describes training first on a broad motion collection, then refining the model on curated motion data and finally using human feedback and reward models to improve instruction following and naturalness. That explains the release's three-stage training claim. It describes how the model was developed; the announced downloadable package specifically includes the trained models and code for generating motion.
- inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
articleExplorationBench: Feedback and Self-Designed Probes Drive Agent Discovery
postHy Image3.5 preview is live. 🚀 Professional-grade image generation, +30% win…
postTencent Hunyuan's EvolveScaler trips up frontier models on evolving facts
postTencent Hunyuan open-sources AuK, a unified speech generation and editing model
Checking sign-in…
Loading comments…