搜索结果

InternVL

InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型 InternVL 家族：利用开源套件缩小与商业多模态模型的差距——GPT-4o 的先驱开源替代方案 InternVL3，一个性能强大的开源多模态大模型。其中InternVL3-78B同时在感知能力和推理能力上同时达到了开源第

Hunyuan3D

腾讯混元大模型旗下最新发布的Hunyuan3D-2.0系列开源模型，迎来了五款产品（Turbo、Pro、Standard、Lite、Vision）的全系列开源，构建起完整的工具链体系，标志着中国大模型技术首次在多模态领域实现完整开源布局。从30秒生成高精度3D资产的开源框架，到覆盖文本、图像、视频的全模态开源体系，腾讯混元大模型正以开放姿态引领一场全球范围内的数字创作革命。 这一突破得益于腾讯自

Supervity AI

Supervity AI 提供一套旨在提升业务效率的智能体。该平台作为公司知识的中心枢纽，根据内部文档提供精准的答案。智能体可以连接上千种不同的软件应用程序，管理涉及多个步骤的工作流程，从而实现现有业务系统的自动化。 用户无需编写代码即可构建自动化流程。名为“协同浏览 AI”的功能可实时指导员工使用软件，同时另一位智能体可以安全自然地处理客户对话。Vision AI 智能代理通过查看图像和视

WiseVision ROS2 MCP Server

🚀 Wayland MCP Server

MCP Server for Wayland

🚀 OpenCV MCP Server

OpenCV MCP Server provides OpenCV's image and video processing capabilities through the Model Context Protocol (MCP). Access powerful computer vision tools for tasks ranging from basic image manipulat

groundlight-mcp-server

MCP Server for Groundlight

🚀 MCP: The CLI-Based Universal AI Application Connector

🚀 OpenClient- The CLI-Based Universal AI Application Connector! An open-source Model Context Protocol (MCP) implementation that turbocharges LLMs by context provisioning standardization. Quickly conne

Model Context Protocol (MCP)

🚀 OpenClient- The CLI-Based Universal AI Application Connector! An open-source Model Context Protocol (MCP) implementation that turbocharges LLMs by context provisioning standardization. Quickly conne

🧠 Vibe Check MCP

The definitive Vibe Coder's sanity check MCP server: Prevent cascading errors in AI workflows by implementing strategic pattern interrupts. Uses tool call "Vibe Check" with LearnLM 1.5 Pro (Gemini API

UI-TARS Desktop

A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.

AI Vision MCP Server

A Model Context Protocol server for AI vision analysis using Gemini Vision API

Azure AI Vision Face MCP-Server

Hosts the Azure-Ai-Vision-Face Liveness Mcp-Server

MCP Server for CVDLT(Computer Vision & Deep Learning Tools)

The repo is based on Model Context procotol of Python SDK, including DL models in CV, and provide the abilities to the LLM or vLLM model

Yahoo Finance MCP Server

This is a Model Context Protocol (MCP) server that provides comprehensive financial data from Yahoo Finance. It allows you to retrieve detailed information about stocks, including historical prices, c

YouTube Vision MCP Server (

MCP (Model Context Protocol) server that utilizes the Google Gemini Vision API to interact with YouTube videos.

Youtube Vision

MCP OpenVision

MCP Server using OpenRouter models to get descriptions for images

AI Vision MCP Server

Mirror of

Solana-MCP-Trading-Server

server that shows trending tokens and integrates Grok, xAI image understanding and vision (interpreted as a vision-capable AI), and Claude's computer use capabilities.

MCP Image Recognition Server

An MCP server that provides image recognition 👀 capabilities using Anthropic and OpenAI vision APIs

PostgreSQL MCP Server

Easily connect to PostgreSQL databases via a plug-and-play MCP server. Supports SELECT, INSERT, UPDATE, and more with prepared statements, automatic connection handling, and full TypeScript support

DreamFit

DreamFit是什么 DreamFit是字节跳动团队联合清华大学深圳国际研究生院、中山大学深圳校区推出的虚拟试衣框架，专门用在轻量级服装为中心的人类图像生成。框架能显著减少模型复杂度和训练成本，基于优化文本提示和特征融合，提高生成图像的质量和一致性。DreamFit能泛化到各种服装、风格和提示指令，生成高质量的人物图像。DreamFit支持与社区控制插件的无缝集成，降低使用门槛。 Dre

Moondream

Moondream是一个免费开源的小型的人工智能视觉语言模型，虽然参数量小（Moondream1仅16亿，Moondream2为18.6亿）但可以提供高性能的视觉处理能力，可在本地计算机甚至移动设备或 Raspberry Pi 上运行，能够快速理解和处理输入的图像信息并对用户提出的问题进行解答。该模型由开发人员vikhyatk推出，使用SigLP、Phi-1.5和LLaVa训练数据集和模型权重初始