代码库
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
Python
ai-infrastructurereinforcement-learningsglangvllm
AuK: An Open-Source Foundational Model for Speech Generation and Editing
Python
deep-learningfoundation-modelspythonpytorchseparationspeaker-extractionspeechspeech-editingspeech-enhancementtext-to-speechzero-shot-tts
HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing
Python
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Python
diffusion-modelsdiffusion-transformervideo-generation
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
Python
Python
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
Python
image-generationnative-multimodal-model
HY-Motion model for 3D human motion or 3D character animation generation.
Python
HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models
Python
aigcdiffusion
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Python
3daiworldmodel
HunyuanVideo-1.5: A leading lightweight video generation model
Python
image-to-videotext-to-videovideo-generation
HY-Embodied: Embodied Foundation Models for Real-World Agents
Python
Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference
Python
Official Implementation of OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Python
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Python
3d3d-aigc3d-generationdiffusion-modelshunyuan3dimage-to-3dshapeshape-generationtext-to-3dtexture-generation
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
Python
3d3d-aigc3d-generationhunyuan3dimage-to-3dshapeshape-generationtext-to-3dtexture-genertaion