{"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/consistent-diffusion-meets-tweedie-training","title":"Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data","arxiv_id":"2404.10177","date":"2024-03-20","proceeding":null,"authors":["Giannis Daras","Alexandros G. Dimakis","Constantinos Daskalakis"],"abstract":"Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. Both Ambient Diffusion and alternative SURE-based approaches for learning diffusion models from corrupted data resort to approximations which deteriorate performance. We present the first framework for training diffusion models that provably sample from the uncorrupted distribution given only noisy training data, solving an open problem in this space. Our key technical contribution is a method that uses a double application of Tweedie's formula and a consistency loss function that allows us to extend sampling at noise levels below the observed data noise. We also provide further evidence that diffusion models memorize from their training sets by identifying extremely corrupted images that are almost perfectly reconstructed, raising copyright and privacy concerns. Our method for training using corrupted samples can be used to mitigate this problem. We demonstrate this by fine-tuning Stable Diffusion XL to generate samples from a distribution using only noisy samples. Our framework reduces the amount of memorization of the fine-tuning dataset, while maintaining competitive performance.","url_abs":"https://arxiv.org/abs/2404.10177v2","url_pdf":"https://arxiv.org/pdf/2404.10177v2.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":"consistent-diffusion-meets-tweedie-training","repo_url":"https://github.com/giannisdaras/ambient-tweedie","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"memorization","task_name":"Memorization"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.10177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10177"}},"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":"deterministic:regex_extraction","url":"https://github.com/giannisdaras/ambienttweedie","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/giannisdaras/ambient-tweedie","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":4,"samples":[{"code_sha256_prefix":"6c02b1ac3d9b6e4c","entry":"load_captions","repo":"giannisdaras/ambient-tweedie","repo_kind":"official","path":"eval_scripts/generate.py","file_url":"https://github.com/giannisdaras/ambient-tweedie/blob/HEAD/eval_scripts/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6c02b1ac3d9b6e4c"}},{"code_sha256_prefix":"d3d9b5fd6b42f66c","entry":"tokenize_prompt","repo":"giannisdaras/ambient-tweedie","repo_kind":"official","path":"train_text_to_image_lora_sdxl.py","file_url":"https://github.com/giannisdaras/ambient-tweedie/blob/HEAD/train_text_to_image_lora_sdxl.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d3d9b5fd6b42f66c"}},{"code_sha256_prefix":"07b37e928c65e319","entry":"load_captions","repo":"giannisdaras/ambient-tweedie","repo_kind":"official","path":"attack_scripts/attack_with_noise.py","file_url":"https://github.com/giannisdaras/ambient-tweedie/blob/HEAD/attack_scripts/attack_with_noise.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"07b37e928c65e319"}},{"code_sha256_prefix":"0612418218ed64e5","entry":"parse_args","repo":"giannisdaras/ambient-tweedie","repo_kind":"official","path":"train_text_to_image_lora_sdxl.py","file_url":"https://github.com/giannisdaras/ambient-tweedie/blob/HEAD/train_text_to_image_lora_sdxl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0612418218ed64e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}