{"url":"/task/conditional-text-to-image-synthesis","name":"Conditional Text-to-Image Synthesis","slug":"conditional-text-to-image-synthesis","description_markdown":"Introducing extra conditions based on the text-to-image generation process, similar to the paradigm of ControlNet.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"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":10,"papers_with_code":8,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/conditional-text-to-image-synthesis-on-mimic","slug":"conditional-text-to-image-synthesis-on-mimic","dataset":"MIMIC-CXR","dataset_url":"/dataset/mimic-cxr","rows_in_archive":13,"metrics":["FID (RadDino)"],"first_row_in_archive_order":{"model":"Sana","paper_title":"CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs","paper_url":"/paper/chexgenbench-a-unified-benchmark-for-fidelity","paper_date":"2025-05-15","arxiv_id":"2505.10496","code_links":[{"title":"Raman1121/CheXGenBench","url":"https://github.com/Raman1121/CheXGenBench"}],"syntology":null}},{"leaderboard":"/sota/conditional-text-to-image-synthesis-on-coco","slug":"conditional-text-to-image-synthesis-on-coco","dataset":"COCO 2017 val","dataset_url":null,"rows_in_archive":12,"metrics":["FID","CLIP Score"],"first_row_in_archive_order":{"model":"LCDG","paper_title":"LaCon: Late-Constraint Diffusion for Steerable Guided Image Synthesis","paper_url":"/paper/late-constraint-diffusion-guidance-for","paper_date":"2023-05-19","arxiv_id":"2305.11520","code_links":[{"title":"AlonzoLeeeooo/LCDG","url":"https://github.com/AlonzoLeeeooo/LCDG"}],"syntology":null}},{"leaderboard":"/sota/conditional-text-to-image-synthesis-on-coco-1","slug":"conditional-text-to-image-synthesis-on-coco-1","dataset":"COCO-MIG","dataset_url":"/dataset/coco-mig","rows_in_archive":5,"metrics":["instance success rate","mIoU"],"first_row_in_archive_order":{"model":"MIGC","paper_title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","paper_url":"/paper/migc-multi-instance-generation-controller-for","paper_date":"2024-02-08","arxiv_id":"2402.05408","code_links":[{"title":"limuloo/migc","url":"https://github.com/limuloo/migc"}],"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":9}}}],"datasets":[{"url":"/dataset/mimic-cxr","name":"MIMIC-CXR","full_name":"MIMIC-CXR","num_papers_in_archive":240},{"url":"/dataset/coco-mig","name":"COCO-MIG","full_name":"COCO-MIG benchmark","num_papers_in_archive":8}],"subtasks":[],"parent_tasks":[{"url":"/task/text-to-image-generation","name":"Text-to-Image Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":8,"of":8,"tagged_in_all":10,"items":[{"url":"/paper/boxdiff-text-to-image-synthesis-with-training","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","date":"2023-07-20","arxiv_id":"2307.10816","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/chexgenbench-a-unified-benchmark-for-fidelity","title":"CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs","date":"2025-05-15","arxiv_id":"2505.10496","repositories_listed":1,"syntology":null},{"url":"/paper/zero-painter-training-free-layout-control-for","title":"Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis","date":"2024-06-06","arxiv_id":"2406.04032","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/migc-multi-instance-generation-controller-for","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","date":"2024-02-08","arxiv_id":"2402.05408","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/instancediffusion-instance-level-control-for","title":"InstanceDiffusion: Instance-level Control for Image Generation","date":"2024-02-05","arxiv_id":"2402.03290","repositories_listed":1,"syntology":{"n":18,"n_ran":17,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/prompt-free-diffusion-taking-text-out-of-text","title":"Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models","date":"2023-05-25","arxiv_id":"2305.16223","repositories_listed":1,"syntology":null},{"url":"/paper/late-constraint-diffusion-guidance-for","title":"LaCon: Late-Constraint Diffusion for Steerable Guided Image Synthesis","date":"2023-05-19","arxiv_id":"2305.11520","repositories_listed":1,"syntology":null},{"url":"/paper/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_unverified":0,"n_pointer_only":0}}],"syntology_records":5,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}