AIGC
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
📦Portable package for running Hunyuan3D 2.0/2.1 on Windows. | 混元 3D 2.0/2.1 整合包
[CVPR Workshop 2025] Code for SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentation
Real-time webcam demo with SmolVLM and llama.cpp server
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
Wan: Open and Advanced Large-Scale Video Generative Models
[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers
[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides [EMNLP 2025]
Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM.
[NeurIPS 2025] Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
SkyReels-V2: Infinite-length Film Generative model
MUSt3R: Multi-view Network for Stereo 3D Reconstruction
A Modular Framework for 3D Generation and Beyond [WIP]
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Official Implementation of [AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models]
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
XVERSE Character UE plugin (XCharacter-UEPlugin) a 3D digital human creation plugin for Unreal Engine 5, developed by XVERSE Technology Inc. (Zhenshen, China).
[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"
Official front-end implementation of ComfyUI