{"url":"/sota/layout-to-image-generation-on-layoutbench-2","task":{"name":"Layout-to-Image Generation","url":"/task/layout-to-image-generation","note":null},"dataset":{"name":"LayoutBench-COCO - Position","url":"/dataset/layoutbench-coco-position"},"category":"Computer Vision","categories":["Computer Vision","Medical","Miscellaneous","Natural Language Processing"],"category_note":null,"description":"Layout-to-image generation its the task to generate a scene based on the given layout. The layout describes the location of the objects to be included in the output image.\r\nIn this section, you can find state-of-the-art leaderboards for Layout-to-image generation.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AP":"higher"}},"counts":{"rows":4,"rows_with_code":3,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"IterInpaint","metrics":{"AP":"39.1"},"uses_additional_data":false,"paper_date":"2023-04-13","paper":"/paper/diagnostic-benchmark-and-iterative-inpainting","paper_url":"https://arxiv.org/abs/2304.06671v3","paper_title":"Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation","code":"https://github.com/j-min/IterInpaint","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"GLIGEN","metrics":{"AP":"38.9"},"uses_additional_data":false,"paper_date":"2023-01-17","paper":"/paper/gligen-open-set-grounded-text-to-image","paper_url":"https://arxiv.org/abs/2301.07093v2","paper_title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","code":"https://github.com/gligen/GLIGEN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"ReCo","metrics":{"AP":"36.4"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/reco-region-controlled-text-to-image","paper_url":"https://arxiv.org/abs/2211.15518v1","paper_title":"ReCo: Region-Controlled Text-to-Image Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"ControlNet","metrics":{"AP":"15.3"},"uses_additional_data":false,"paper_date":"2023-02-10","paper":"/paper/adding-conditional-control-to-text-to-image","paper_url":"https://arxiv.org/abs/2302.05543v3","paper_title":"Adding Conditional Control to Text-to-Image Diffusion Models","code":"https://github.com/microsoft/visual-chatgpt","n_code_links":12,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}