{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/layout-to-image-generation","name":"Layout-to-Image Generation","slug":"layout-to-image-generation","description_markdown":"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.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":41,"papers_with_code":24,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/layout-to-image-generation-on-coco-stuff-2","slug":"layout-to-image-generation-on-coco-stuff-2","dataset":"COCO-Stuff 64x64","dataset_url":"/dataset/coco-stuff","rows_in_archive":5,"metrics":["FID","Inception Score"],"first_row_in_archive_order":{"model":"OC-GAN","paper_title":"Object-Centric Image Generation from Layouts","paper_url":"/paper/object-centric-image-generation-from-layouts","paper_date":"2020-03-16","arxiv_id":"2003.07449","code_links":[],"syntology":null}},{"leaderboard":"/sota/layout-to-image-generation-on-coco-stuff-3","slug":"layout-to-image-generation-on-coco-stuff-3","dataset":"COCO-Stuff 128x128","dataset_url":"/dataset/coco-stuff","rows_in_archive":5,"metrics":["FID","Inception Score","SceneFID"],"first_row_in_archive_order":{"model":"CAL2IM","paper_title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","paper_url":"/paper/context-aware-layout-to-image-generation-with","paper_date":"2021-03-22","arxiv_id":"2103.11897","code_links":[{"title":"wtliao/layout2img","url":"https://github.com/wtliao/layout2img"}],"syntology":null}},{"leaderboard":"/sota/layout-to-image-generation-on-coco-stuff-4","slug":"layout-to-image-generation-on-coco-stuff-4","dataset":"COCO-Stuff 256x256","dataset_url":"/dataset/coco","rows_in_archive":5,"metrics":["FID","Inception Score","LPIPS"],"first_row_in_archive_order":{"model":"LayoutDiffusion (25steps)","paper_title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","paper_url":"/paper/layoutdiffusion-controllable-diffusion-model","paper_date":"2023-03-30","arxiv_id":"2303.17189","code_links":[{"title":"zgctroy/layoutdiffusion","url":"https://github.com/zgctroy/layoutdiffusion"},{"title":"dcdcvgroup/layout-diffusion-mindspore","url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore"}],"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/layoutdiffusion-controllable-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2303.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17189"}},"official":{"repos":["dcdcvgroup/layout-diffusion-mindspore"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["named_in_paper","official"]}}}},{"leaderboard":"/sota/layout-to-image-generation-on-visual-genome-3","slug":"layout-to-image-generation-on-visual-genome-3","dataset":"Visual Genome 128x128","dataset_url":"/dataset/visual-genome","rows_in_archive":5,"metrics":["FID","Inception Score","SceneFID"],"first_row_in_archive_order":{"model":"LayoutDiffusion","paper_title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","paper_url":"/paper/layoutdiffusion-controllable-diffusion-model","paper_date":"2023-03-30","arxiv_id":"2303.17189","code_links":[{"title":"zgctroy/layoutdiffusion","url":"https://github.com/zgctroy/layoutdiffusion"},{"title":"dcdcvgroup/layout-diffusion-mindspore","url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore"}],"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/layoutdiffusion-controllable-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2303.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17189"}},"official":{"repos":["dcdcvgroup/layout-diffusion-mindspore"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["named_in_paper","official"]}}}},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-1","slug":"layout-to-image-generation-on-layoutbench-1","dataset":"LayoutBench-COCO - Number","dataset_url":"/dataset/layoutbench-coco","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"IterInpaint","paper_title":"Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation","paper_url":"/paper/diagnostic-benchmark-and-iterative-inpainting","paper_date":"2023-04-13","arxiv_id":"2304.06671","code_links":[{"title":"j-min/IterInpaint","url":"https://github.com/j-min/IterInpaint"},{"title":"j-min/LayoutBench-COCO","url":"https://github.com/j-min/LayoutBench-COCO"}],"syntology":null}},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-2","slug":"layout-to-image-generation-on-layoutbench-2","dataset":"LayoutBench-COCO - Position","dataset_url":"/dataset/layoutbench-coco-position","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"IterInpaint","paper_title":"Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation","paper_url":"/paper/diagnostic-benchmark-and-iterative-inpainting","paper_date":"2023-04-13","arxiv_id":"2304.06671","code_links":[{"title":"j-min/IterInpaint","url":"https://github.com/j-min/IterInpaint"},{"title":"j-min/LayoutBench-COCO","url":"https://github.com/j-min/LayoutBench-COCO"}],"syntology":null}},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-3","slug":"layout-to-image-generation-on-layoutbench-3","dataset":"LayoutBench-COCO - Size","dataset_url":"/dataset/layoutbench-coco-size","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"IterInpaint","paper_title":"Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation","paper_url":"/paper/diagnostic-benchmark-and-iterative-inpainting","paper_date":"2023-04-13","arxiv_id":"2304.06671","code_links":[{"title":"j-min/IterInpaint","url":"https://github.com/j-min/IterInpaint"},{"title":"j-min/LayoutBench-COCO","url":"https://github.com/j-min/LayoutBench-COCO"}],"syntology":null}},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-4","slug":"layout-to-image-generation-on-layoutbench-4","dataset":"LayoutBench-COCO - Combination","dataset_url":"/dataset/layoutbench-coco-combination","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"IterInpaint","paper_title":"Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation","paper_url":"/paper/diagnostic-benchmark-and-iterative-inpainting","paper_date":"2023-04-13","arxiv_id":"2304.06671","code_links":[{"title":"j-min/IterInpaint","url":"https://github.com/j-min/IterInpaint"},{"title":"j-min/LayoutBench-COCO","url":"https://github.com/j-min/LayoutBench-COCO"}],"syntology":null}},{"leaderboard":"/sota/layout-to-image-generation-on-visual-genome-2","slug":"layout-to-image-generation-on-visual-genome-2","dataset":"Visual Genome 64x64","dataset_url":"/dataset/visual-genome","rows_in_archive":4,"metrics":["FID","Inception Score"],"first_row_in_archive_order":{"model":"OC-GAN","paper_title":"Object-Centric Image Generation from Layouts","paper_url":"/paper/object-centric-image-generation-from-layouts","paper_date":"2020-03-16","arxiv_id":"2003.07449","code_links":[],"syntology":null}},{"leaderboard":"/sota/layout-to-image-generation-on-visual-genome-4","slug":"layout-to-image-generation-on-visual-genome-4","dataset":"Visual Genome 256x256","dataset_url":"/dataset/visual-genome","rows_in_archive":4,"metrics":["FID","Inception Score","LPIPS"],"first_row_in_archive_order":{"model":"LayoutDiffusion","paper_title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","paper_url":"/paper/layoutdiffusion-controllable-diffusion-model","paper_date":"2023-03-30","arxiv_id":"2303.17189","code_links":[{"title":"zgctroy/layoutdiffusion","url":"https://github.com/zgctroy/layoutdiffusion"},{"title":"dcdcvgroup/layout-diffusion-mindspore","url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore"}],"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/layoutdiffusion-controllable-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2303.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17189"}},"official":{"repos":["dcdcvgroup/layout-diffusion-mindspore"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["named_in_paper","official"]}}}},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench","slug":"layout-to-image-generation-on-layoutbench","dataset":"LayoutBench","dataset_url":"/dataset/layoutbench","rows_in_archive":3,"metrics":["AP"],"first_row_in_archive_order":{"model":"IterInpaint","paper_title":"Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation","paper_url":"/paper/diagnostic-benchmark-and-iterative-inpainting","paper_date":"2023-04-13","arxiv_id":"2304.06671","code_links":[{"title":"j-min/IterInpaint","url":"https://github.com/j-min/IterInpaint"},{"title":"j-min/LayoutBench-COCO","url":"https://github.com/j-min/LayoutBench-COCO"}],"syntology":null}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/visual-genome","name":"Visual Genome","full_name":"","num_papers_in_archive":1256},{"url":"/dataset/coco-stuff","name":"COCO-Stuff","full_name":"Common Objects in COntext-stuff","num_papers_in_archive":338},{"url":"/dataset/layoutbench-coco-combination","name":"LayoutBench-COCO - Combination","full_name":"","num_papers_in_archive":4},{"url":"/dataset/layoutbench-coco","name":"LayoutBench-COCO - Number","full_name":"","num_papers_in_archive":4},{"url":"/dataset/layoutbench-coco-position","name":"LayoutBench-COCO - Position","full_name":"","num_papers_in_archive":4},{"url":"/dataset/layoutbench-coco-size","name":"LayoutBench-COCO - Size","full_name":"","num_papers_in_archive":4},{"url":"/dataset/layoutbench","name":"LayoutBench","full_name":"","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/image-generation","name":"Image Generation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":41,"of":41,"of_with_code":24,"tagged_in_all":41,"counts":{"archive_papers_tagged":41,"with_a_code_link":24,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":41,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/high-resolution-image-synthesis-with-latent","slug":"high-resolution-image-synthesis-with-latent","title":"High-Resolution Image Synthesis with Latent Diffusion Models","date":"2021-12-20","arxiv_id":"2112.10752","repositories_listed":41,"syntology":{"n":28,"n_ran":22,"n_constructed":0,"n_ran_checked":8,"n_instrument":14,"n_unverified":6,"n_honours":1,"n_violates":4,"n_no_contract":3,"n_pointer_only":10,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 4 violated, 3 with no contract checked; 14 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/high-resolution-image-synthesis-with-latent#ran","syntology_url":"https://syntology.ai/paper/2112.10752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10752"}},"official":null}},{"url":"/paper/adding-conditional-control-to-text-to-image","slug":"adding-conditional-control-to-text-to-image","title":"Adding Conditional Control to Text-to-Image Diffusion Models","date":"2023-02-10","arxiv_id":"2302.05543","repositories_listed":12,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adding-conditional-control-to-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2302.05543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05543"}},"official":{"repos":["lllyasviel/controlnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/image-synthesis-from-reconfigurable-layout","slug":"image-synthesis-from-reconfigurable-layout","title":"Image Synthesis From Reconfigurable Layout and Style","date":"2019-08-20","arxiv_id":"1908.07500","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/image-synthesis-from-reconfigurable-layout#ran","syntology_url":"https://syntology.ai/paper/1908.07500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07500"}},"official":{"repos":["iVMCL/LostGANs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/image-generation-from-scene-graphs","slug":"image-generation-from-scene-graphs","title":"Image Generation from Scene Graphs","date":"2018-04-04","arxiv_id":"1804.01622","repositories_listed":4,"syntology":{"n":21,"n_ran":20,"n_constructed":0,"n_ran_checked":20,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":1,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/image-generation-from-scene-graphs#ran","syntology_url":"https://syntology.ai/paper/1804.01622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.01622"}},"official":null}},{"url":"/paper/learning-layout-and-style-reconfigurable-gans","slug":"learning-layout-and-style-reconfigurable-gans","title":"Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis","date":"2020-03-25","arxiv_id":"2003.11571","repositories_listed":3,"syntology":null},{"url":"/paper/diagnostic-benchmark-and-iterative-inpainting","slug":"diagnostic-benchmark-and-iterative-inpainting","title":"Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation","date":"2023-04-13","arxiv_id":"2304.06671","repositories_listed":2,"syntology":null},{"url":"/paper/layoutdiffusion-controllable-diffusion-model","slug":"layoutdiffusion-controllable-diffusion-model","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","date":"2023-03-30","arxiv_id":"2303.17189","repositories_listed":2,"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/layoutdiffusion-controllable-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2303.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17189"}},"official":{"repos":["dcdcvgroup/layout-diffusion-mindspore"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/learning-canonical-representations-for-scene","slug":"learning-canonical-representations-for-scene","title":"Learning Canonical Representations for Scene Graph to Image Generation","date":"2019-12-16","arxiv_id":"1912.07414","repositories_listed":2,"syntology":{"n":17,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/learning-canonical-representations-for-scene#ran","syntology_url":"https://syntology.ai/paper/1912.07414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.07414"}},"official":{"repos":["roeiherz/CanonicalSg2Im"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/specifying-object-attributes-and-relations-in","slug":"specifying-object-attributes-and-relations-in","title":"Specifying Object Attributes and Relations in Interactive Scene Generation","date":"2019-09-11","arxiv_id":"1909.05379","repositories_listed":2,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/specifying-object-attributes-and-relations-in#ran","syntology_url":"https://syntology.ai/paper/1909.05379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05379"}},"official":{"repos":["ashual/scene_generation"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tolo-a-two-stage-training-free-layout-to","slug":"tolo-a-two-stage-training-free-layout-to","title":"ToLo: A Two-Stage, Training-Free Layout-To-Image Generation Framework For High-Overlap Layouts","date":"2025-03-03","arxiv_id":"2503.01667","repositories_listed":1,"syntology":null},{"url":"/paper/hico-hierarchical-controllable-diffusion","slug":"hico-hierarchical-controllable-diffusion","title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation","date":"2024-10-18","arxiv_id":"2410.14324","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":3,"n_instrument":10,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hico-hierarchical-controllable-diffusion#ran","syntology_url":"https://syntology.ai/paper/2410.14324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14324"}},"official":{"repos":["360cvgroup/hico_t2i"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-the-training-and-evaluation-of","slug":"rethinking-the-training-and-evaluation-of","title":"Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation","date":"2024-09-07","arxiv_id":"2409.04847","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":2,"n_no_contract":4,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 2 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rethinking-the-training-and-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2409.04847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04847"}},"official":{"repos":["cplusx/rich_context_l2i"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/training-free-composite-scene-generation-for","slug":"training-free-composite-scene-generation-for","title":"Training-free Composite Scene Generation for Layout-to-Image Synthesis","date":"2024-07-18","arxiv_id":"2407.13609","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-supervision-makes-layout-to-image","slug":"adversarial-supervision-makes-layout-to-image","title":"Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive","date":"2024-01-16","arxiv_id":"2401.08815","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adversarial-supervision-makes-layout-to-image#ran","syntology_url":"https://syntology.ai/paper/2401.08815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08815"}},"official":{"repos":["boschresearch/aldm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-blueprint-enabling-text-to-image","slug":"llm-blueprint-enabling-text-to-image","title":"LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts","date":"2023-10-16","arxiv_id":"2310.10640","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llm-blueprint-enabling-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2310.10640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10640"}},"official":{"repos":["hananshafi/llmblueprint"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/guided-image-synthesis-via-initial-image","slug":"guided-image-synthesis-via-initial-image","title":"Guided Image Synthesis via Initial Image Editing in Diffusion Model","date":"2023-05-05","arxiv_id":"2305.03382","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/guided-image-synthesis-via-initial-image#ran","syntology_url":"https://syntology.ai/paper/2305.03382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.03382"}},"official":{"repos":["UT-Mao/Initial-Noise-Editing"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/freestyle-layout-to-image-synthesis","slug":"freestyle-layout-to-image-synthesis","title":"Freestyle Layout-to-Image Synthesis","date":"2023-03-25","arxiv_id":"2303.14412","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/freestyle-layout-to-image-synthesis#ran","syntology_url":"https://syntology.ai/paper/2303.14412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14412"}},"official":{"repos":["essunny310/freestylenet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/gligen-open-set-grounded-text-to-image","slug":"gligen-open-set-grounded-text-to-image","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","date":"2023-01-17","arxiv_id":"2301.07093","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/gligen-open-set-grounded-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2301.07093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.07093"}},"official":{"repos":["gligen/GLIGEN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/modeling-image-composition-for-complex-scene","slug":"modeling-image-composition-for-complex-scene","title":"Modeling Image Composition for Complex Scene Generation","date":"2022-06-02","arxiv_id":"2206.00923","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modeling-image-composition-for-complex-scene#ran","syntology_url":"https://syntology.ai/paper/2206.00923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00923"}},"official":{"repos":["johndreamer/twfa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/interactive-image-synthesis-with-panoptic","slug":"interactive-image-synthesis-with-panoptic","title":"Interactive Image Synthesis with Panoptic Layout Generation","date":"2022-03-04","arxiv_id":"2203.02104","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/interactive-image-synthesis-with-panoptic#ran","syntology_url":"https://syntology.ai/paper/2203.02104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02104"}},"official":{"repos":["wb-finalking/PLGAN"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/attrlostgan-attribute-controlled-image","slug":"attrlostgan-attribute-controlled-image","title":"AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style","date":"2021-03-25","arxiv_id":"2103.13722","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-layout-to-image-generation-with","slug":"context-aware-layout-to-image-generation-with","title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","date":"2021-03-22","arxiv_id":"2103.11897","repositories_listed":1,"syntology":null},{"url":"/paper/generating-annotated-high-fidelity-images","slug":"generating-annotated-high-fidelity-images","title":"Generating Annotated High-Fidelity Images Containing Multiple Coherent Objects","date":"2020-06-22","arxiv_id":"2006.12150","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-image-manipulation-using-scene","slug":"semantic-image-manipulation-using-scene","title":"Semantic Image Manipulation Using Scene Graphs","date":"2020-04-07","arxiv_id":"2004.03677","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/semantic-image-manipulation-using-scene#ran","syntology_url":"https://syntology.ai/paper/2004.03677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03677"}},"official":{"repos":["he-dhamo/simsg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":null,"slug":"psi-sampler-initial-particle-sampling-for-smc","title":"Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models","date":"2025-06-02","arxiv_id":"2506.01320","repositories_listed":0,"syntology":null},{"url":null,"slug":"plangen-towards-unified-layout-planning-and","title":"PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models","date":"2025-03-13","arxiv_id":"2503.10127","repositories_listed":0,"syntology":null},{"url":null,"slug":"creatilayout-siamese-multimodal-diffusion","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","date":"2024-12-05","arxiv_id":"2412.03859","repositories_listed":0,"syntology":null},{"url":null,"slug":"boundary-attention-constrained-zero-shot","title":"Boundary Attention Constrained Zero-Shot Layout-To-Image Generation","date":"2024-11-15","arxiv_id":"2411.10495","repositories_listed":0,"syntology":null},{"url":null,"slug":"ltos-layout-controllable-text-object","title":"LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions","date":"2024-04-21","arxiv_id":"2404.13579","repositories_listed":0,"syntology":null},{"url":null,"slug":"objblur-a-curriculum-learning-approach-with","title":"ObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation","date":"2024-04-11","arxiv_id":"2404.07564","repositories_listed":0,"syntology":null},{"url":null,"slug":"divcon-divide-and-conquer-for-progressive","title":"DivCon: Divide and Conquer for Progressive Text-to-Image Generation","date":"2024-03-11","arxiv_id":"2403.06400","repositories_listed":0,"syntology":null},{"url":null,"slug":"layout-to-image-generation-with-localized","title":"Layout-to-Image Generation with Localized Descriptions using ControlNet with Cross-Attention Control","date":"2024-02-20","arxiv_id":"2402.13404","repositories_listed":0,"syntology":null},{"url":null,"slug":"divide-and-conquer-language-models-can-plan","title":"Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation","date":"2024-01-28","arxiv_id":"2401.15688","repositories_listed":0,"syntology":null},{"url":null,"slug":"smartmask-context-aware-high-fidelity-mask","title":"SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control","date":"2023-12-08","arxiv_id":"2312.05039","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssmg-spatial-semantic-map-guided-diffusion","title":"SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation","date":"2023-08-20","arxiv_id":"2308.10156","repositories_listed":0,"syntology":null},{"url":null,"slug":"law-diffusion-complex-scene-generation-by","title":"LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts","date":"2023-08-13","arxiv_id":"2308.06713","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-geometric-control-into-text-to","title":"GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation","date":"2023-06-07","arxiv_id":"2306.04607","repositories_listed":0,"syntology":null},{"url":null,"slug":"layoutdiffuse-adapting-foundational-diffusion","title":"LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation","date":"2023-02-16","arxiv_id":"2302.08908","repositories_listed":0,"syntology":null},{"url":"/paper/reco-region-controlled-text-to-image","slug":"reco-region-controlled-text-to-image","title":"ReCo: Region-Controlled Text-to-Image Generation","date":"2022-11-23","arxiv_id":"2211.15518","repositories_listed":0,"syntology":null},{"url":"/paper/object-centric-image-generation-from-layouts","slug":"object-centric-image-generation-from-layouts","title":"Object-Centric Image Generation from Layouts","date":"2020-03-16","arxiv_id":"2003.07449","repositories_listed":0,"syntology":null},{"url":"/paper/image-generation-from-layout","slug":"image-generation-from-layout","title":"Image Generation from Layout","date":"2018-11-28","arxiv_id":"1811.11389","repositories_listed":0,"syntology":null}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":17,"papers_where_code_ran_first_page":"/task/layout-to-image-generation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/layout-to-image-generation/papers/ran/1","json":"/task/layout-to-image-generation/papers/ran/1.json","rows":17}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"af947bae40a5594f8181c149c896f1cd872e8784aecf84159aef0c51cff115c8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}