{"url":"/dataset/spright","name":"SPRIGHT","full_name":null,"description_markdown":"SPRIGHT is the first, large-scale vision-language dataset that focuses on spatial relationships. It contains ~6M images that have been re-captioned with a synthetic focus.","description_withheld":null,"homepage":"https://huggingface.co/datasets/SPRIGHT-T2I/spright","introduced_date":"2024-04-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/getting-it-right-improving-spatial","title":"Getting it Right: Improving Spatial Consistency in Text-to-Image Models","first_author":"Agneet Chatterjee","url":null},"license":null,"modalities":[],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SPRIGHT"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"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."}