{"url":"/dataset/textatlaseval","name":"TextAtlasEval","full_name":null,"description_markdown":"*A Dense-text Image Benchmark to evaluate large generation model's ability on text generation.*","description_withheld":null,"homepage":"https://textatlas5m.github.io","introduced_date":"2025-02-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/textatlas5m-a-large-scale-dataset-for-dense","title":"TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation","first_author":"Alex Jinpeng Wang","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"},{"name":"Text within image generation","url":"/task/text-within-image-generation","datasets_with_task":"/datasets/task/text-within-image-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TextAtlasEval"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-generation-on-textatlaseval","task":"Image Generation","dataset_variant":"TextAtlasEval","rows":7,"metrics":["TextVsionBlend OCR (F1 Score)","TextVisionBlend OCR (Accuracy)","TextVisionBlend OCR (Cer)","TextVisionBlend FID","TextVisionBlend Clip Score","StyledTextSynth OCR (F1 Score)","StyledTextSynth OCR (Accuracy)","StyledTextSynth OCR (Cer)","StyledTextSynth FID","StyledTextSynth Clip Score","TextScenesHQ OCR (F1 Score)","TextScenesHQ OCR (Accuracy)","TextScenesHQ OCR (Cer)","TextScenesHQ FID","TextScenesHQ Clip Score"],"first_row_in_archive_order":{"model":"Grok3","paper":null,"metrics":{"StyledTextSynth Clip Score":"0.2938","StyledTextSynth FID":"80.33","StyledTextSynth OCR (Accuracy)":"15.82","StyledTextSynth OCR (Cer)":"0.73","StyledTextSynth OCR (F1 Score)":"21.40","TextScenesHQ Clip Score":"0.3197","TextScenesHQ FID":"-","TextScenesHQ OCR (Accuracy)":"35.07","TextScenesHQ OCR (Cer)":"0.57","TextScenesHQ OCR (F1 Score)":"37.94","TextVisionBlend Clip Score":"0.1697","TextVisionBlend FID":"-","TextVisionBlend OCR (Accuracy)":"41.54","TextVisionBlend OCR (Cer)":"0.57","TextVsionBlend OCR (F1 Score)":"44.22"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/infinity-mm-scaling-multimodal-performance","title":"Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data","date":"2024-10-24","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pixart-s-weak-to-strong-training-of-diffusion","title":"PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","date":"2024-03-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/textdiffuser-2-unleashing-the-power-of","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","date":"2023-11-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/anytext-multilingual-visual-text-generation","title":"AnyText: Multilingual Visual Text Generation And Editing","date":"2023-11-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":4,"samples_unverified":15,"pointer_only_for_licence":0,"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":3,"samples_harvested":34,"samples_ran":10,"samples_unverified":24,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":1,"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."}