Visual ChatGPT 通过连接ChatGPT和一系列视觉基础模型,在聊天过程中实现了图像的发送和接收。
项目地址
https://github.com/microsoft/visual-chatgpt
论文
https://arxiv.org/abs/2303.04671
Demo
架构
快速开始
# create a new environment
conda create -n visgpt python=3.8
# activate the new environment
conda activate visgpt
# prepare the basic environments
pip install -r requirement.txt
# download the visual foundation models
bash download.sh
# prepare your private openAI private key
export OPENAI_API_KEY={Your_Private_Openai_Key}
# create a folder to save images
mkdir ./image
# Start Visual ChatGPT !
python visual_chatgpt.py
翻译
http://visualchatgpt.cn/