Sharenet.ai

Day arching a pawn and sharing for the king!
Mistral AI 发布 Small 3.1 模型:开源多模态能力再升级

Mistral AI releases Small 3.1 model: another upgrade in open source multimodal capabilities

Mistral AI has recently announced the launch of its latest model, Mistral Small 3.1, which it claims is the best choice in its class today. This new model builds on the foundation of Mistral Small 3 in terms of text performance, multimodal...
3mos ago
0550
JigsawStack:提供多种小型专用AI模型API服务

JigsawStack: Serving up a variety of small, specialized AI model APIs

综合介绍 JigsawStack 是一个专为开发者打造的AI工具平台。它提供多种小型AI模型的API服务,帮助用户快速集成功能到自己的应用程序中。核心特点是速度快,全球延迟低至200毫秒,可用性高达9...
3mos ago
0567
Dify v1.1.0 知识库新增“元数据”智能过滤器

Dify v1.1.0 New "Metadata" Smart Filter for Knowledge Bases

在信息爆炸的时代,如何从海量数据中快速、精准地定位关键信息,已成为企业和个人知识管理的核心挑战。近日,Dify 产品团队发布了 v1.1.0 版本,并创新性地推出了以“元数据”为核心的知识过滤器功能...
3mos ago
0581
AI Logo:AI快速生成定制化品牌Logo

AI Logo: AI Quickly Generates Customized Brand Logos

General Introduction AI Logo is an open source AI application project with the goal of helping users quickly generate personalized brand logos through artificial intelligence. It combines powerful AI techniques such as Stable Diffusion and DeepAI to allow users to enter simple brand...
3mos ago
0580
Docs:开源的协作笔记和文档管理工具

Docs: open source collaborative notes and document management tools

综合介绍 Docs 是一个开源的协作笔记和文档管理平台,由 suitenumerique 团队开发。它使用 Django 和 React 技术构建,目标是提供一个简单易用的工具,帮助用户记录笔记、管理...
3mos ago
0611
OCR 开源项目深度盘点:2025 年不容错过的 Top 10

OCR Open Source Project In-Depth Inventory: Top 10 Not to Miss in 2025

OCR 技术能够将图像中的文字信息转换为可编辑和可处理的文本数据。简单来说,就是识别和提取图片上的文字。 接下来,我们将深入评测 GitHub 上 Star 数最多的 10 个 OCR 开源项目,为你...
3mos ago
0691
SmartRead:自动标注技术PDF文档并提供相关引用源

SmartRead: Automatically annotate technical PDF documents and provide relevant citation sources

Comprehensive Introduction SmartRead is an AI-based open source tool designed for technical documents. It can automatically analyze PDF files, mark key content, such as important terms, titles or core ideas to help users quickly understand complex documents. At the same time, it can also provide with the main document...
3mos ago
0668
Hunyuan3D-2:腾讯开源的高分辨率3D模型生成工具

Hunyuan3D-2: Tencent open source high-resolution 3D model generation tool

General Introduction Hunyuan3D-2 is an open source project developed by Tencent to generate high-resolution 3D models from text or images. It consists of two core components: shape generation model (Hunyuan3D-DiT) and texture generation model (Hunyuan3D...
3mos ago
0704
LangManus:支持多智能体协作的开源AI自动化框架

LangManus: an open source AI automation framework supporting multi-intelligence collaboration

综合介绍 LangManus 是一个开源的 AI 自动化框架,托管在 GitHub 上。它由一群前同事在业余时间开发,属于学术驱动项目,目标是结合语言模型和专用工具,完成网页搜索、数据爬取和代码执行等...
3mos ago
0786
Gemini 迟来的“Canvas”功能,一起体验他能做什么

Gemini's belated "Canvas" feature, experience what it can do!

Gemini 最近更新有些频繁,非顺序整理: 正式上线 Veo2 推理模型在 Google AI Studio 、Gemini(缩水版) 分别上线 原生支持图像生成编辑的多模态模型:Gemini ...
3mos ago
0509