xiaozhoushi

new-pac

翻墙-科学上网、自由上网、免费科学上网、免费翻墙、油管youtube、fanqiang、软件、VPN、一键翻墙浏览器，vps一键搭建翻墙服务器脚本/教程，免费shadowsocks/ss/ssr/v2ray/goflyway账号/节点，翻墙梯子，电脑、手机、iOS、安卓、windows、Mac、Linux、路由器翻墙、科学上网、youtube视频下载、美区apple id共享账号

grok-1

Grok open release

chinese-independent-developer

👩🏿‍💻👨🏾‍💻👩🏼‍💻👨🏽‍💻👩🏻‍💻**独立开发者项目列表 -- 分享大家都在做什么

llama3

The official Meta Llama 3 GitHub site

llm.c

LLM training in simple, raw C/CUDA

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

supervision

We write your reusable computer vision tools. 💜

ui

Simple UI examples from my social media

nerf

Code release for NeRF (Neural Radiance Fields)

douyin

Vue3 + Pinia 仿抖音，Vue 在移动端的最佳实践 . Imitate TikTok ，Vue Best practices on Mobile

self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程

instruct-pix2pix

DeepSpeedExamples

Example models using DeepSpeed

dust3r

DUSt3R: Geometric 3D Vision Made Easy

TripoSR

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

nccl

Optimized primitives for collective multi-GPU communication

ComfyUI-3D-Pack

An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)

DreamCraft3D

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

arch-guide

✨ archlinux 简明指南 | 本指南包含从 archlinux 安装、显卡驱动、日常软件配置、多媒体制作、编程等你可能需要的全部内容 | 提供在线文档 ✨

nvdiffrast

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

leetcode.nvim

A Neovim plugin enabling you to solve LeetCode problems.

OpenLRM

An open-source impl. of Large Reconstruction Models

OpenCLAY

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

RepViT

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

CRM

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

Era3D

ViewDiff

ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).

Hit-leetcode

面试助手，使用ocr+大模型反击八股文