Tencent-Hunyuan

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

HunyuanVideo-1.5: A leading lightweight video generation model

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

HY-Motion model for 3D human motion or 3D character animation generation.

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

AuK: An Open-Source Foundational Model for Speech Generation and Editing

We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.

WorldClaw: Agentic 3D Open-world Generation at Scale

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

[ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

HY-Embodied: Embodied Foundation Models for Real-World Agents

Tencent Hunyuan A13B (short as Hunyuan-A13B), an innovative and open-source LLM built on a fine-grained MoE architecture.

Official Implementation of OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning

Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition

HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​

Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

CL-bench: A Benchmark for Context Learning

Hunyuan 3D Part Segmentation and Generation Pipeline

Hy-Nomas: Towards Free-form Interactive World Generation

Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency

[CVPR-2025] The code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

Unleashing Vecset Diffusion Model for Fast Shape Generation / within 1 Second (ICCV'25 Highlight)

From Vision-Language-Action Models to a Real-World Robot Learning Stack

Official code for paper: Scaling Mesh Generation via Compressive Tokenization [CVPR'25]

[Tech Report] A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing

Research artifacts from Hyra (/ˈhaɪ.rɑː/)

Official code for HiLS-Attention

flex-block-attn: an efficient block sparse attention computation library

RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination

Official Implementation of SAGE-GRPO:Manifold-Aware Exploration for Reinforcement Learning in Video Generation

Implementation of GradLoc from the Tencent Hunyuan blog "Stabilizing RLVR via Token-level Gradient Diagnosis and Layerwise Clipping".

iFSQ & LlamaGen-REPA

The official code of [ICLR 2026] TFPI: Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners

Tencent Hunyuan 7B (short as Hunyuan-7B) is one of the large language dense models of Tencent Hunyuan

[NeurIPS 2026] Code for our resarch paper "SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking"

HY-Embodied-0.5-X: An Enhanced Embodied Foundation Model for Real-World Agents

[SIGGRAPH2026] Official code for SIGGRAPH2026 paper: R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow