Repositories list

• HunyuanVision

  Public
  0•70•0•0•Updated Oct 21, 2025Oct 21, 2025

• HunyuanWorld-1.0

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

  3d3d-generationworld-models+ 6scene-generationimage-to-3daigctext-to-3dworld-modelhunyuan3d

  Python

  •

  Other

  •187•2.3k•19•1•Updated Oct 20, 2025Oct 20, 2025

• Hunyuan3D-Part

  Public
  Hunyuan 3D Part Segmentation and Generation Pipeline

  3d3d-generationhunyuan3d

  Python

  •

  Other

  •26•310•2•3•Updated Oct 19, 2025Oct 19, 2025

• Hunyuan3D-Omni

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

  shape3d3d-generation+ 4multimodalimage-to-3d3d-aigchunyuan3d

  Python

  •

  Other

  •27•420•7•0•Updated Oct 17, 2025Oct 17, 2025

• Hunyuan3D-2.1

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

  shape3d3d-generation+ 6shape-generationimage-to-3dtext-to-3d3d-aigchunyuan3dtexture-genertaion

  Python

  •

  Other

  •296•2.3k•104•18•Updated Oct 17, 2025Oct 17, 2025

• Hunyuan3D-1

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

  textgeneration3d+ 13dgen

  Python

  •

  Other

  •274•3.4k•26•2•Updated Oct 17, 2025Oct 17, 2025

• HunyuanWorld-Voyager

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

  3d3d-generationimage-to-video+ 6world-modelsscene-generationimage-to-3daigcworld-modelhunyuan3d

  Python

  •

  Other

  •115•1.3k•13•1•Updated Oct 17, 2025Oct 17, 2025

• Hunyuan-GameCraft-1.0

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

  Python

  •

  Other

  •68•605•14•0•Updated Oct 16, 2025Oct 16, 2025

• HunyuanVideo-Avatar

  Public
  Python

  •

  Other

  •306•1.9k•68•2•Updated Oct 16, 2025Oct 16, 2025

• HunyuanCustom

  Public
  HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

  video-editingvideo-generationimage-to-video+ 3diffusion-modelsaudio-drivenimage-to-video-generation

  Python

  •

  Other

  •106•1.2k•34•1•Updated Oct 15, 2025Oct 15, 2025

• HunyuanImage-3.0

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

  image-generationnative-multimodal-model

  Python

  •

  Other

  •93•2.3k•27•0•Updated Oct 14, 2025Oct 14, 2025

• HunyuanImage-2.1

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

  image-generationtext-to-imagediffusion-models+ 2aigcdiffusion-transformer

  Python

  •

  Other

  •48•650•11•2•Updated Oct 14, 2025Oct 14, 2025

• MixGRPO

  Public
  MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

  reinforcement-learningdiffusiongrpo

  Python

  •

  Other

  •43•1k•3•0•Updated Oct 13, 2025Oct 13, 2025

• SRPO

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

  Python

  •

  Other

  •35•1.1k•21•0•Updated Oct 11, 2025Oct 11, 2025

• FlashVDM

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

  Python

  •

  Other

  •10•279•2•0•Updated Oct 7, 2025Oct 7, 2025

• Hunyuan3D-2

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

  shape3dtexture-generation+ 73d-generationshape-generationdiffusion-modelsimage-to-3dtext-to-3d3d-aigchunyuan3d

  Python

  •

  Other

  •1.2k•12k•202•12•Updated Oct 6, 2025Oct 6, 2025

• HunyuanVideo-Foley

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

  ttavideo-to-audiotext-to-audio+ 5text-to-videofoley-sound-synthesisfoley-artaigc-audiotext-video-to-audio

  Python

  •

  Other

  •84•1.2k•15•0•Updated Sep 28, 2025Sep 28, 2025

• ArtifactsBenchmark

  Public
  Python

  •

  Other

  •15•232•1•1•Updated Sep 19, 2025Sep 19, 2025

• Hunyuan-MT

  Public
  Python

  •

  Other

  •54•601•30•1•Updated Sep 10, 2025Sep 10, 2025

• HunyuanVideo

  Public
  HunyuanVideo: A Systematic Framework For Large Video Generation Model

  video-generationdiffusion-modelsdiffusion-transformer

  Python

  •

  Other

  •1.1k•11k•141•14•Updated Aug 27, 2025Aug 27, 2025

• Tencent-Hunyuan-7B-0124

  Public
  Python

  •

  Other

  •8•28•0•1•Updated Aug 21, 2025Aug 21, 2025

• AutoCodeBenchmark

  Public
  Python

  •

  Other

  •7•115•1•0•Updated Aug 15, 2025Aug 15, 2025

• Hunyuan-7B

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

  Python

  •

  Other

  •11•66•8•2•Updated Aug 11, 2025Aug 11, 2025

• Hunyuan-4B

  Public
  Python

  •

  Other

  •3•15•1••Updated Aug 5, 2025Aug 5, 2025

• Hunyuan-1.8B

  Public
  Python

  •

  Other

  •5•32•1•1•Updated Aug 5, 2025Aug 5, 2025

• Hunyuan-0.5B

  Public
  Python

  •

  Other

  •6•45•2•1•Updated Aug 5, 2025Aug 5, 2025

• bpt

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

  Python

  •

  Other

  •12•278•5•0•Updated Jul 30, 2025Jul 30, 2025

• Hunyuan-A13B

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

  Python

  •

  Other

  •114•802•22•1•Updated Jul 8, 2025Jul 8, 2025

• C3-Benchmark

  Public
  C^3-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking

  Python

  •

  Other

  •3•34•0•0•Updated Jun 30, 2025Jun 30, 2025

• UnifiedReward

  Public
  Official implementation of UnifiedReward & UnifiedReward-Think

  Python

  •

  MIT License

  •36•16•12•7•Updated Jun 18, 2025Jun 18, 2025