{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/getting-it-right-improving-spatial","title":"Getting it Right: Improving Spatial Consistency in Text-to-Image Models","arxiv_id":"2404.01197","date":"2024-04-01","proceeding":null,"authors":["Agneet Chatterjee","Gabriela Ben Melech Stan","Estelle Aflalo","Sayak Paul","Dhruba Ghosh","Tejas Gokhale","Ludwig Schmidt","Hannaneh Hajishirzi","Vasudev Lal","Chitta Baral","Yezhou Yang"],"abstract":"One of the key shortcomings in current text-to-image (T2I) models is their inability to consistently generate images which faithfully follow the spatial relationships specified in the text prompt. In this paper, we offer a comprehensive investigation of this limitation, while also developing datasets and methods that support algorithmic solutions to improve spatial reasoning in T2I models. We find that spatial relationships are under-represented in the image descriptions found in current vision-language datasets. To alleviate this data bottleneck, we create SPRIGHT, the first spatially focused, large-scale dataset, by re-captioning 6 million images from 4 widely used vision datasets and through a 3-fold evaluation and analysis pipeline, show that SPRIGHT improves the proportion of spatial relationships in existing datasets. We show the efficacy of SPRIGHT data by showing that using only $\\sim$0.25% of SPRIGHT results in a 22% improvement in generating spatially accurate images while also improving FID and CMMD scores. We also find that training on images containing a larger number of objects leads to substantial improvements in spatial consistency, including state-of-the-art results on T2I-CompBench with a spatial score of 0.2133, by fine-tuning on <500 images. Through a set of controlled experiments and ablations, we document additional findings that could support future work that seeks to understand factors that affect spatial consistency in text-to-image models.","url_abs":"https://arxiv.org/abs/2404.01197v2","url_pdf":"https://arxiv.org/pdf/2404.01197v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"getting-it-right-improving-spatial","repo_url":"https://github.com/SPRIGHT-T2I/SPRIGHT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[{"slug":"spright","name":"SPRIGHT","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.01197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01197"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SPRIGHT-T2I/SPRIGHT","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"75533a417777ed7f","entry":"create_payload","repo":"SPRIGHT-T2I/SPRIGHT","repo_kind":"official","path":"eval/gpt4/eval_with_gpt4.py","file_url":"https://github.com/SPRIGHT-T2I/SPRIGHT/blob/HEAD/eval/gpt4/eval_with_gpt4.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"75533a417777ed7f"}},{"code_sha256_prefix":"57bfaec2f02fdac2","entry":"encode_image","repo":"SPRIGHT-T2I/SPRIGHT","repo_kind":"official","path":"eval/gpt4/eval_with_gpt4.py","file_url":"https://github.com/SPRIGHT-T2I/SPRIGHT/blob/HEAD/eval/gpt4/eval_with_gpt4.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57bfaec2f02fdac2"}},{"code_sha256_prefix":"61d2ea68e47261f9","entry":"sort_file_paths","repo":"SPRIGHT-T2I/SPRIGHT","repo_kind":"official","path":"eval/gpt4/collate_gpt4_results.py","file_url":"https://github.com/SPRIGHT-T2I/SPRIGHT/blob/HEAD/eval/gpt4/collate_gpt4_results.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"61d2ea68e47261f9"}},{"code_sha256_prefix":"4cdc2946cd076c08","entry":"copy_images","repo":"SPRIGHT-T2I/SPRIGHT","repo_kind":"official","path":"eval/gpt4/create_eval_dataset.py","file_url":"https://github.com/SPRIGHT-T2I/SPRIGHT/blob/HEAD/eval/gpt4/create_eval_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4cdc2946cd076c08"}},{"code_sha256_prefix":"7907eec720d8a01d","entry":"get_ratings_from_json","repo":"SPRIGHT-T2I/SPRIGHT","repo_kind":"official","path":"eval/gpt4/collate_gpt4_results.py","file_url":"https://github.com/SPRIGHT-T2I/SPRIGHT/blob/HEAD/eval/gpt4/collate_gpt4_results.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7907eec720d8a01d"}},{"code_sha256_prefix":"b153819851508e8f","entry":"get_response","repo":"SPRIGHT-T2I/SPRIGHT","repo_kind":"official","path":"eval/gpt4/eval_with_gpt4.py","file_url":"https://github.com/SPRIGHT-T2I/SPRIGHT/blob/HEAD/eval/gpt4/eval_with_gpt4.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b153819851508e8f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}