{"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/the-emergence-of-reproducibility-and","title":"The Emergence of Reproducibility and Generalizability in Diffusion Models","arxiv_id":"2310.05264","date":"2023-10-08","proceeding":null,"authors":["Huijie Zhang","Jinfan Zhou","Yifu Lu","Minzhe Guo","Peng Wang","Liyue Shen","Qing Qu"],"abstract":"In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as \"consistent model reproducibility\": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs. We confirm this phenomenon through comprehensive experiments, implying that different diffusion models consistently reach the same data distribution and scoring function regardless of diffusion model frameworks, model architectures, or training procedures. More strikingly, our further investigation implies that diffusion models are learning distinct distributions affected by the training data size. This is supported by the fact that the model reproducibility manifests in two distinct training regimes: (i) \"memorization regime\", where the diffusion model overfits to the training data distribution, and (ii) \"generalization regime\", where the model learns the underlying data distribution. Our study also finds that this valuable property generalizes to many variants of diffusion models, including those for conditional use, solving inverse problems, and model fine-tuning. Finally, our work raises numerous intriguing theoretical questions for future investigation and highlights practical implications regarding training efficiency, model privacy, and the controlled generation of diffusion models.","url_abs":"https://arxiv.org/abs/2310.05264v4","url_pdf":"https://arxiv.org/pdf/2310.05264v4.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":"the-emergence-of-reproducibility-and","repo_url":"https://github.com/huijieZH/Diffusion-Model-Generalizability","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"memorization","task_name":"Memorization"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.05264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05264"}},"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/huijieZH/Diffusion-Model-Generalizability","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"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":"640adf50ba465604","entry":"TransformSamples","repo":"huijieZH/Diffusion-Model-Generalizability","repo_kind":"listed","path":"edm/sscd.py","file_url":"https://github.com/huijieZH/Diffusion-Model-Generalizability/blob/HEAD/edm/sscd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"640adf50ba465604"}},{"code_sha256_prefix":"553a32f93376dc01","entry":"get_exp_bias_batch","repo":"huijieZH/Diffusion-Model-Generalizability","repo_kind":"listed","path":"edm/generate.py","file_url":"https://github.com/huijieZH/Diffusion-Model-Generalizability/blob/HEAD/edm/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"553a32f93376dc01"}},{"code_sha256_prefix":"7effd95926009645","entry":"normal_distribution_batch","repo":"huijieZH/Diffusion-Model-Generalizability","repo_kind":"listed","path":"edm/generate.py","file_url":"https://github.com/huijieZH/Diffusion-Model-Generalizability/blob/HEAD/edm/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7effd95926009645"}},{"code_sha256_prefix":"00dcc1be26a2af0f","entry":"edm_sampler","repo":"huijieZH/Diffusion-Model-Generalizability","repo_kind":"listed","path":"edm/generate.py","file_url":"https://github.com/huijieZH/Diffusion-Model-Generalizability/blob/HEAD/edm/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00dcc1be26a2af0f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}