{"url":"/dataset/laion-coco","name":"LAION COCO","full_name":null,"description_markdown":"**LAION-COCO** is the world’s largest dataset of 600M generated high-quality captions for publicly available web-images. The images are extracted from the english subset of Laion-5B with an ensemble of BLIP L/14 and 2 CLIP versions (L/14 and RN50x64). This dataset allow models to produce high quality captions for images.\r\n\r\nSource: [LAION COCO: 600M SYNTHETIC CAPTIONS FROM LAION2B-EN](https://laion.ai/blog/laion-coco/)\r\n\r\nImage Source: [https://laion.ai/blog/laion-coco/](https://laion.ai/blog/laion-coco/)","description_withheld":null,"homepage":"https://laion.ai/blog/laion-coco/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["LAION COCO"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-image-generation-on-laion-coco","task":"Text-to-Image Generation","dataset_variant":"LAION COCO","rows":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"Parti Finetuned","paper":"/paper/scaling-autoregressive-models-for-content","metrics":{"FID":"8.39"},"code_links":[{"title":"lucidrains/parti-pytorch","url":"https://github.com/lucidrains/parti-pytorch"},{"title":"syang-lab/Pathway_Autoregressive_Text2Image_Model","url":"https://github.com/syang-lab/Pathway_Autoregressive_Text2Image_Model"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/scaling-autoregressive-models-for-content","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","date":"2022-06-22","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":3,"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":1,"samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":3,"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."}