Dataset · poloclub
2M Stable Diffusion images with prompts
poloclub/diffusiondb
2M Stable Diffusion images with prompts and hyperparameters from real users.
What's inside
DiffusionDB is the first large-scale text-to-image prompt dataset. It contains 2M images generated by Stable Diffusion using prompts and hyperparameters specified by real users. Prompts are in English; metadata includes generation parameters.
What you can do with it
- Training and evaluating text-to-image models
- Detecting generated images and deepfakes
- Studying the relationship between prompts and generative models
- Tasks
- Text → image, Image → text
- Languages
- English
- Size
- over 1T rows
- Downloads this month
- 29.2K
- Likes
- 678
Models trained on it
- FredZhang7/distilgpt2-stable-diffusion-v2Text generation 2.3K
- amd/Nitro-1-SDText → image 835
- mradermacher/distilgpt2-stable-diffusion-v2-i1-GGUF 319
- amd/Nitro-1-PixArtText → image 263
- saggamer/horizon-1Text → image 210
- amd/Nitro-T-0.6BText → image 163
- mradermacher/distilgpt2-stable-diffusion-v2-GGUF 145
- vllm-sr/Decision-1.0-Route-0.6BZero shot classification 101
How to load it
from datasets import load_dataset
ds = load_dataset("poloclub/diffusiondb")