ComfyUI-KepOpenAI

ComfyUI-KepOpenAI
★ 30

GPT-4V图像理解文本生成OpenAI 集成
用于将图片与文本提示发送到 OpenAI GPT-4V 的 ComfyUI 节点，返回基于图像与提示的上下文语义文本回复，便于在工作流中实现视觉+语言处理。
💡 在 ComfyUI 中用图像和提示生成基于上下文的文本回复。
🍴 19 Forks💻 Python🔄 2024-08-20
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/c73fe210bae7
📦 requirements.txt
openai>=1.1
📄 README

ComfyUI-KepOpenAI

Overview

ComfyUI-KepOpenAI is a user-friendly node that serves as an interface to the GPT-4 with Vision (GPT-4V) API. This integration facilitates the processing of images coupled with text prompts, leveraging the capabilities of the OpenAI API to generate text completions that are contextually relevant to the provided inputs.

Features

  • Accepts both an image and a text prompt as input.
  • Integrates seamlessly with the OpenAI GPT-4V API to provide intelligent text completions.
  • Requires an OpenAI API key, which should be securely stored and provided as an environment variable.

    • Configuration

    To utilize this node, you must set the OPEN_AI_API_KEY environment variable with your OpenAI API key. This ensures that the API is accessible and requests are authenticated properly.