# Installation and Startup Guide

### Windows (

If the automatic installation fails, please refer to the manual installation instructions at the bottom.

1. Double-click install_windows.bat

to run and install all necessary dependencies.

2. Once installed, you can launch GPT4V-Image-Captioner in a terminal by double-clicking `start_Windows.bat'

.

3. If you hold down Ctrl and click the URL address in the terminal

(or copy the URL address to open in a browser), you will be redirected to the Gradio application interface in your default browser.

4. Please enter OpenAI's official or third-party GPT-4v API Key and API URL at the top of the interface

, set the image address, and then you can mark the image.

### Linux/macOS 1

.

Open a terminal and navigate to the project directory: cd gpt4V-image-captioner2.

Make the installation script and startup script executable using the following command: chmod +x install_linux_mac.sh; chmod +x Start_linux_mac.sh 3.

Execute the installation script:.

/install_linux_mac.sh

4. Run the startup script in the terminal to start GPT4V-image-captioner

.

.

/Start_linux_mac.sh

5. Copy the URL address displayed on the terminal and open the Gradio application interface in

your browser.

6. Please enter OpenAI's official or third-party GPT-4v API Key and API URL at the top of the interface

, set the image address, and then you can mark the image.

### Windows Manual Installation Instructions 1

. Press Win + R to open the command prompt. Type `cmd` and press `Enter`

.

2.

Clone the repository locally using the following command: git clone https://github.com/jiayev/GPT4V-Image-Captioner 3.

Once cloning is complete, switch to the cloned directory: cd gpt4V-image-captioner 4.

Before installing the dependent libraries, type the following command in the command prompt and press `Enter` to check if the computer already has Python installed: python --version If not installed, an error message will be displayed.

Please visit [Official Python Download Page] (https://www.python.org/downloads/)

and follow the instructions to install it.

5.

Create a virtual environment called `myenv` to avoid polluting the overall Python environment: python -m venv myenv 6.

Activate the virtual environment you just created:

myenv

\ Scripts\ activate 7.

Update `pip` to the latest version:

python -m

pip install --upgrade pip 8.

Install libraries such as requests, gradio, and tqdm in a virtual environment: pip install scipy networkx wordcloud matplotlib pillow tqdm gradio requests

9. After completing these steps, you can launch GPT4V-Image-Captioner by double-clicking the `start_Windows.bat` file

.