Tencent-Hunyuan

HunyuanVideo-1.5: A leading lightweight video generation model

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

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

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

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

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

CL-bench: A Benchmark for Context Learning

iFSQ & LlamaGen-REPA

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

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

HunyuanVideo: A Systematic Framework For Large Video Generation Model

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

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

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

Fast and Universal 3D reconstruction model for versatile tasks

Hunyuan 3D Part Segmentation and Generation Pipeline

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

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

(arXiv) MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

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

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

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