Website

Tencent-Hunyuan

Open-source projects on GitHub: HunyuanVideo, HunyuanVideo-1.5 and HunyuanOCR

  • 15 produits actifs

Portefeuille de produits consolidé

  • AuK

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

    Machine Learning Model TrainingOpen Source
  • GradLoc

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

    Llm OrchestrationOpen Source
  • HY-WorldPlay

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

    3d ModelingOpen Source
  • Hunyuan-A13B

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

    Llm OrchestrationOpen Source
  • Hunyuan-GameCraft-1.0

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

    Ai Video CreationOpen Source
  • HunyuanCustom

    HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

    Video EditingOpen Source
  • HunyuanImage-2.1

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

    Ai Image EditingOpen Source
  • HunyuanOCR

    HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

    Ocr ProcessingOpen Source
  • HunyuanPortrait

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

    Ai Video CreationOpen Source
  • HunyuanVideo

    HunyuanVideo: A Systematic Framework For Large Video Generation Model

    Ai Video CreationOpen Source
  • HunyuanVideo-1.5

    HunyuanVideo-1.5: A leading lightweight video generation model

    Ai Video CreationOpen Source
  • HunyuanVideo-Foley

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

    Ai Video CreationOpen Source
  • HunyuanWorld-Voyager

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

    Ai Video CreationOpen Source
  • Hyra-results

    Research artifacts from Hyra (/ˈhaɪ.rɑː/)

    Llm OrchestrationOpen Source
  • OmniWeaving

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

    Ai Video CreationOpen Source

Profil de l'entreprise et stratégie

Tencent-Hunyuan maintient 13 projets open-source sur GitHub, y compris HunyuanVideo, HunyuanVideo-1.5 et HunyuanOCR. Le langage principal est Python.

Empreinte open source

15 dépôts28.9K étoiles
Visiter l'organisation GitHub

Save & manage the vendor's products in Productapp.

Save and manage this vendor's products in Productapp.

Start free trial