{"url":"/dataset/diffusiondb","name":"DiffusionDB","full_name":null,"description_markdown":"**DiffusionDB** is a large-scale text-to-image prompt dataset. It contains 2 million images generated by Stable Diffusion using prompts and hyperparameters specified by real users.","description_withheld":null,"homepage":"https://poloclub.github.io/diffusiondb/","introduced_date":"2022-10-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/diffusiondb-a-large-scale-prompt-gallery","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","first_author":"Zijie J. Wang","url":null},"license":{"name":"CC0 1.0 License","url":"https://creativecommons.org/publicdomain/zero/1.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Text to Image Generation","url":"/task/text-to-image-generation-1","datasets_with_task":"/datasets/task/text-to-image-generation-1"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DiffusionDB"],"data_loaders":[{"repo":"https://github.com/poloclub/diffusiondb","url":"https://huggingface.co/datasets/poloclub/diffusiondb","frameworks":[]}],"num_papers_in_archive":70,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-image-generation-on-diffusiondb","task":"Text to Image Generation","dataset_variant":"DiffusionDB","rows":0,"metrics":["Fréchet Inception Distance","Inception Score","Similarity Score (CLIP)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}