DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models

crown jewel figure
DiffusionDB is the first large-scale dataset containing 14 million Stable Diffusion images and their text prompts and hyperparameters. This dataset provides exciting research opportunities in prompt engineering, deepfake detection, as well as understanding and debugging large text-to-image generative models.
With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often unclear how a model reacts to different prompts and what the best prompts are. To help researchers tackle these critical challenges, we introduce DiffusionDB, the first large-scale text-to-image prompt dataset. DiffusionDB contains 14 million images generated by Stable Diffusion using prompts and hyperparameters specified by real users. We analyze prompts in the dataset and discuss key properties of these prompts. The unprecedented scale and diversity of this human-actuated dataset provide exciting research opportunities in understanding the interplay between prompts and generative models, detecting deepfakes, and designing human-AI interaction tools to help users more easily use these models. DiffusionDB is publicly available at: https://poloclub.github.io/diffusiondb.
DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models
  title = {{{DiffusionDB}}: {{A}} Large-Scale Prompt Gallery Dataset for Text-to-Image Generative Models},
  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: {{Long}} Papers)},
  author = {Wang, Zijie J. and Montoya, Evan and Munechika, David and Yang, Haoyang and Hoover, Benjamin and Chau, Duen Horng},
  year = {2023},
  url = {https://aclanthology.org/2023.acl-long.51}