{"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/pathldm-text-conditioned-latent-diffusion","title":"PathLDM: Text conditioned Latent Diffusion Model for Histopathology","arxiv_id":"2309.00748","date":"2023-09-01","proceeding":null,"authors":["Srikar Yellapragada","Alexandros Graikos","Prateek Prasanna","Tahsin Kurc","Joel Saltz","Dimitris Samaras"],"abstract":"To achieve high-quality results, diffusion models must be trained on large datasets. This can be notably prohibitive for models in specialized domains, such as computational pathology. Conditioning on labeled data is known to help in data-efficient model training. Therefore, histopathology reports, which are rich in valuable clinical information, are an ideal choice as guidance for a histopathology generative model. In this paper, we introduce PathLDM, the first text-conditioned Latent Diffusion Model tailored for generating high-quality histopathology images. Leveraging the rich contextual information provided by pathology text reports, our approach fuses image and textual data to enhance the generation process. By utilizing GPT's capabilities to distill and summarize complex text reports, we establish an effective conditioning mechanism. Through strategic conditioning and necessary architectural enhancements, we achieved a SoTA FID score of 7.64 for text-to-image generation on the TCGA-BRCA dataset, significantly outperforming the closest text-conditioned competitor with FID 30.1.","url_abs":"https://arxiv.org/abs/2309.00748v2","url_pdf":"https://arxiv.org/pdf/2309.00748v2.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":"pathldm-text-conditioned-latent-diffusion","repo_url":"https://github.com/cvlab-stonybrook/pathldm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.00748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00748"}},"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/cvlab-stonybrook/pathldm","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":5,"ran_violates":3,"ran_fixture":1,"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":12,"ran":11,"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":12,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/modules/diffusionmodules/model.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/modules/diffusionmodules/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"fe5dd5258046898c","entry":"always","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/modules/x_transformer.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/modules/x_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fe5dd5258046898c"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/models/diffusion/classifier.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/models/diffusion/classifier.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"cb49209c125de1b4","entry":"get_timestep_embedding","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/modules/diffusionmodules/model.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/modules/diffusionmodules/model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb49209c125de1b4"}},{"code_sha256_prefix":"b1368330cf0f5642","entry":"isimage","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1368330cf0f5642"}},{"code_sha256_prefix":"d72762b700feee6f","entry":"ismap","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d72762b700feee6f"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/modules/diffusionmodules/model.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/modules/diffusionmodules/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"d48d8354986e3b0e","entry":"uniform_on_device","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/models/diffusion/ddpm.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/models/diffusion/ddpm.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d48d8354986e3b0e"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"f9bd2e83191afad1","entry":"log_txt_as_img","repo":"cvlab-stonybrook/pathldm","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/cvlab-stonybrook/pathldm/blob/HEAD/ldm/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9bd2e83191afad1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}