Skip to content

Dataset · Goku-OpenLab

Prompts and generations for GPT Image 2

Goku-OpenLab/gpt-image-2-prompts-datasets

Over 15 thousand English and Chinese prompts with metadata and generated images from GPT Image 2.

What's inside

Contains over 15,000 pairs of text prompts, metadata, and generated images for OpenAI's GPT Image 2 model. The total archive size exceeds 5 GB, with texts presented in English and Chinese.

What you can do with it

  • Training or fine-tuning LoRA for image generators in the style of GPT Image 2
  • Training models for automatic prompt enhancement and expansion
Tasks
Text → image
Languages
English, Chinese
Size
10K–100K rows
Downloads this month
45.8K
Likes
22

How to load it

from datasets import load_dataset

ds = load_dataset("Goku-OpenLab/gpt-image-2-prompts-datasets")