Dataset structure for train_text_to_image_lora.py

[HripsimeS]

Hello. I am trying to use train_text_to_image_lora.py script following the instructions https://github.com/huggingface/diffusers/tree/main/examples/text_to_image

I get errors on data structure and don't know what is the issue on my side.
I have a folder data where I have folder image and csv file.

C:/Users/XXX//data/

├── images/
│ ├── image1.jpg
│ ├── image2.jpg
│ └── ...
└── captions.csv

Image folder contain images and csv file contains two columns (image names and captions)

image, caption
image1.jpg, A dragon flying through fire
image2.jpg, A knight in shining armor

Please can you let me know how I should organize my dataset to be able to run the training.

[SahilCarterr]

You need to create dataset according to huggingFace Dataset. Here is the link for tutorial . LINK
@HripsimeS