haiyang's repositories
AnyV2V
Perform Video Editing with only one image. Now with gradio demo
awesome-low-level-design
Learn Low Level Design (LLD) and prepare for interviews using free resources.
biliplus
🧩 A Chrome/Edge extension to feel better in bilibili.com
cohere-toolkit
Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.
ComfyUI-Phi-3-mini
Using Phi-3-mini in ComfyUI
corenet
CoreNet: A library for training deep neural networks
douyin2
Vue3 + Pinia + Vite5 仿抖音,完全度90% . Imitate TikTok with 90% completeness
efficient-kan
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
Funkin
A rhythm game made with HaxeFlixel
IDM-VTON
IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
instructor
structured outputs for llms
it-tool
Collection of handy online tools for developers, with great UX.
kan-gpt
The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling
llama3-Chinese-chat
Llama3 中文仓库(聚合资料:各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、部署教程视频 & 文档)
llm-scraper
Turn any webpage into structured data using LLMs
lms
LM Studio in your terminal
maestro2
A framework for Claude Opus to intelligently orchestrate subagents.
OpenCRISPR
AI-generated gene editing systems
ProgrammingVTuberLogos
High-quality PNGs for logos I made for fun
pywinassistant
The first open source Large Action Model generalist Artificial Narrow Intelligence that controls completely human user interfaces by only using natural language. PyWinAssistant utilizes Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models.
Quansheng_UV-K5_PCB_R51-V1.4_PCB_Reversing_Rev._0.9
Reverse engineering of the Quansheng UV-K5 V1.4 PCB in KiCad 7
Scrapegraph-ai
Python scraper based on AI
tiny11builder
Scripts to build a trimmed-down Windows 11 image.
tixcraft_bot
MaxBot open source code bot
tov-template
vite + vue3 + ts 开箱即用现代开发模板 | vite + vue3 + ts out-of-the-box modern development template
unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
videoGigaGanHub
VideoGigaGAN is a new generative VSR model that can produce videos with high-frequency details and temporal consistency.
webllama
Llama-3 agents that can browse the web by following instructions and talking to you
xtuner
An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM, Llama, Baichuan, Qwen, ChatGLM)