{"url":"/dataset/t2i-compbench","name":"T2I-CompBench","full_name":null,"description_markdown":"T2I-CompBench is a comprehensive benchmark for open-world compositional text-to-image generation, consisting of 6,000 compositional textual prompts from 3 categories (attribute binding, object relationships, and complex compositions) and 6 sub-categories (color binding, shape binding, texture binding, spatial relationships, non-spatial relationships, and complex compositions).","description_withheld":null,"homepage":"https://karine-h.github.io/T2I-CompBench/","introduced_date":"2023-07-12","introduced_date_note":null,"introduced_by":null,"license":{"name":"MIT License","url":"https://github.com/Karine-Huang/T2I-CompBench/blob/main/License.txt"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"}],"languages":[],"variants":["T2I-CompBench"],"data_loaders":[],"num_papers_in_archive":67,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-image-generation-on-t2i-compbench","task":"Text-to-Image Generation","dataset_variant":"T2I-CompBench","rows":2,"metrics":["Color","Shape","Texture","Complex","Non-Spatial","Spatial"],"first_row_in_archive_order":{"model":"Emu3","paper":"/paper/emu3-next-token-prediction-is-all-you-need","metrics":{"Color":"0.7913","Shape":"0.5846","Texture":"0.7422"},"code_links":[{"title":"baaivision/emu3","url":"https://github.com/baaivision/emu3"},{"title":"flagopen/flagscale","url":"https://github.com/flagopen/flagscale"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/emu3-next-token-prediction-is-all-you-need","title":"Emu3: Next-Token Prediction is All You Need","date":"2024-09-27","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","date":"2023-09-30","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":9,"samples_ran":5,"samples_unverified":4,"pointer_only_for_licence":2,"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."}