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

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.