RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

The ultimate training toolkit for finetuning diffusion models

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

📚 从零开始的大语言模型原理与实践教程

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

Using Low-rank adaptation to quickly fine-tune diffusion models.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

SkyRL: A Modular Full-stack RL Library for LLMs

Official electron build of draw.io

An open source implementation of CLIP.

Accelerator on how to finetune Microsoft's Florance-2 model for a variety of computer vision use cases.

A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like YOLO11, RT-DETR, SAM …

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

dLLM: Simple Diffusion Language Modeling

FIBO is a SOTA, first open-source, JSON-native text-to-image model built for controllable, predictable, and legally safe image generation.

Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

A simple online fake REST API server

Simple and fast JSON database

Get a full fake REST API with zero coding in less than 30 seconds (seriously)

DeepMake

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs

A little Python library for making simple Electron-like HTML/JS GUI apps

PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

OCR model that handles complex tables, forms, handwriting with full layout.

Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM.