Train deepseek r1-like reasoning LLM with ease | 轻松训练1个deepseek r1类的推理LLM

Janus-Series: Unified Multimodal Understanding and Generation Models

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

yolov8 车牌检测 车牌识别 中文车牌识别 检测 支持12种中文车牌 支持双层车牌

A simple, easy-to-hack GraphRAG implementation

This is a ComfyUI-Windows implementation of the image animation projects -> UniAnimate and Animate-X.

CogVideoX-5B-I2V ori model lora train.

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Memory-Guided Diffusion for Expressive Talking Video Generation

HunyuanVideo: A Systematic Framework For Large Video Generation Model

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

crnn chinese_plate_recognition

Computer Vision-Based Tennis Analysis System

This repository contains the source code for the paper First Order Motion Model for Image Animation

实时互动的GPT数字人

Custom Nodes for Comfyui

This is the official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.

Deep RL for MPC control of Quadruped Robot Locomotion

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

The Render workbench

PuLID-Flux ComfyUI implementation

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

基于大模型的智能对话客服工具，支持微信、拼多多、千牛、哔哩哔哩、抖音企业号、抖音、抖店、微博聊天、小红书专业号运营、小红书、知乎等平台接入，可选择 GPT3.5/GPT4.0/ 懒人百宝箱 （后续会支持更多平台），能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业 AI 应用。

微信小程序商城，微信小程序微店