Dataset Name

Dataset Description

This dataset contains images and their corresponding text captions. It was created for the purpose of finetuning stable diffusion using lora. The images are sourced from instagram of some random artist, and the captions are written/designed to provide accurate descriptions of the images.

Dataset Summary

Number of Images: 109
Number of Captions: 109
Image Format: JPG/PNG
Caption Format: Text

Example Usage

Here is how you can load and use the dataset:

from datasets import load_dataset

dataset = load_dataset("Gutema/image-insta")
print(dataset)