|
--- |
|
tags: |
|
- image |
|
- text |
|
- dataset |
|
- captions |
|
license: mit |
|
--- |
|
|
|
# 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: |
|
|
|
```python |
|
from datasets import load_dataset |
|
|
|
dataset = load_dataset("Gutema/image-insta") |
|
print(dataset) |
|
|
