Call Me Maybe's repositories
Cool-GenAI-Fashion-Papers
🧢🕶️🥼👖👟🧳 A curated list of cool resources about GenAI-Fashion, including 📝papers, 👀workshops, 🚀companies & products, ...
CRUD_RAG
CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
dify
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
dust3r
DUSt3R: Geometric 3D Vision Made Easy
flashinfer
FlashInfer: Kernel Library for LLM Serving
Fooocus
Focus on prompting and generating
grok-1
Grok open release
Grounded-Segment-Anything
Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
IDM-VTON
IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
LLM_Solution
ADB + PAI-EAS + LLM + LangChain
MaxKB
💬 基于 LLM 大语言模型的知识库问答系统。开箱即用，支持快速嵌入到第三方业务系统，1Panel 官方出品。
MediaCrawler
小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫
one-person-businesses-methodology-v2.0
《一人企业方法论》第二版，也适合做其他副业（比如自媒体、电商、数字商品）的非技术人群。
onediff
OneDiff: An out-of-the-box acceleration library for diffusion models.
Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
PDFparser
Here is a demo for PDF parser (Including OCR, object detection tools)
QAnything
Question and Answer based on Anything.
rag-search
RAG Search API
StableVITON
[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On
street-tryon-benchmark
StreetTryOn: A Benchmark for In-the-Wild Virtual Try-On and Cross-Domain Virtual Try-On
swift
ms-swift is a framework for LLM finetuning, inference, and deployment. It supports a wide range of models (such as LLaMA, Qwen, ChatGLM, Yi, Internlm, Mistral, Mixtral, Baichuan, etc.) and training methods (including LoRA, LoRA+, QLoRA, Full, LLaMA-Pro, LongLoRA, NEFTune, etc.)
TexTeller
TexTeller can convert image to latex formulas (image2latex, latex OCR) with higher accuracy and exhibits superior generalization ability, enabling it to cover most usage scenarios.