Provide unified multimodal models for understanding, reasoning, generation, and editing across text and visual data.

✨ Enhance web accessibility in real-time with this browser extension that empowers users to identify and fix common issues for a better online experience.

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

WordPress plugin that leverages OpenAI's Vision API to automatically generate descriptive alt text for images, enhancing accessibility and SEO.

A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.

Vision + LLM pipeline: YOLOv8 object detection, GPT-4V scene understanding, and automated visual QA with streaming API

Production multimodal RAG pipeline: ingests PDFs, images, and tables with GPT-4V understanding and hybrid vector retrieval

Vision-Language-Action system for humanoid manipulation. Achieves 77% accuracy on real-world cooking videos.

[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

[CVPR 2024 Oral] 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

[CVPR'25 highlight] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

[NeurIPS'24] SpatialEval: a benchmark to evaluate spatial reasoning abilities of MLLMs and LLMs

Code for ICLR'24 workshop ME-FoMo-How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation

[NeurIPS 2024] An official implementation of "ShareGPT4Video: Improving Video Understanding and Generation with Better Captions"

GPT-4V(ision) module for use with Autodistill.

[ECCV 2024] ShareGPT4V: Improving Large Multi-modal Models with Better Captions

How well do the GPT-4V, Gemini Pro Vision, and Claude 3 Opus models perform zero-shot vision tasks on data structures?

ShareGPT4Omni: Towards Building Omni Large Multi-modal Models with Comprehensive Multi-modal Annotations

How a Picture of Car Damage Can File Your Insurance Claim

Try openai assistant api apps on Google Colab for free. Awesome assistant API Demos!