🤖 Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.

Enhanced ChatGPT Clone: Features OpenAI, GPT-4 Vision, Bing, Anthropic, OpenRouter, Google Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development

Effective prompting for Large Multimodal Models like GPT-4 Vision, LLaVA or CogVLM. 🔥

Cool experiments at the intersection of Computer Vision and Sports ⚽🏃

High quality resources & applications for LLMs, multi-modal models and VectorDBs

【新增Vision识图】免费的基于ChatGPT API的安卓端语音助手，可通过音量键唤起并进行语音交流，支持联网、Vision拍照识图、连续对话、提问模板、3.5/4.0接口、Markdown渲染等功能

SGPT is a command-line tool that provides a convenient way to interact with OpenAI models, enabling users to run queries, generate shell commands and produce code directly from the terminal.

Convert a screenshot to a working Flutter app.

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

Extract information, summarize, ask questions, and search videos using OpenAI's Vision API 🚀🎦

ChatGPT wrapper in your TTY

Desktop AI Assistant powered by GPT-4, GPT-4 Vision, GPT-3.5, Langchain LLMs and DALL-E 3 with chat, completion, vision, image generation and analysis, code and command execution, file upload and download, speech synthesis and recognition, web access, memory, context storage, prompt presets, plugins, assistants and more. Windows and Linux versions.

GPT-4 Vision Chatbot examples

SirChatalot is a Telegram bot powered by ChatGPT (with vision via GPT-4V) or YandexGPT. Speech-to-text is done by Whisper.

A Discord LLM chat bot | OpenAI API | Mistral API | GPT-4 Turbo with vision | Mixtral 8X7B | Streamed responses | And more 🔥

GPT 4 Turbo Vision with Chainlit

Pixie: Computer Vision AI Engineer assistant

This sample project integrates OpenAI's GPT-4 Vision, with advanced image recognition capabilities, and DALL·E 3, the state-of-the-art image generation model, with the Chat completions API. This powerful combination allows for simultaneous image creation and analysis.

Object detection using Open AI Vision Model

Chat with your images using GPT-4 Vision!