{"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/blackout-diffusion-generative-diffusion","title":"Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces","arxiv_id":"2305.11089","date":"2023-05-18","proceeding":null,"authors":["Javier E Santos","Zachary R. Fox","Nicholas Lubbers","Yen Ting Lin"],"abstract":"Typical generative diffusion models rely on a Gaussian diffusion process for training the backward transformations, which can then be used to generate samples from Gaussian noise. However, real world data often takes place in discrete-state spaces, including many scientific applications. Here, we develop a theoretical formulation for arbitrary discrete-state Markov processes in the forward diffusion process using exact (as opposed to variational) analysis. We relate the theory to the existing continuous-state Gaussian diffusion as well as other approaches to discrete diffusion, and identify the corresponding reverse-time stochastic process and score function in the continuous-time setting, and the reverse-time mapping in the discrete-time setting. As an example of this framework, we introduce ``Blackout Diffusion'', which learns to produce samples from an empty image instead of from noise. Numerical experiments on the CIFAR-10, Binarized MNIST, and CelebA datasets confirm the feasibility of our approach. Generalizing from specific (Gaussian) forward processes to discrete-state processes without a variational approximation sheds light on how to interpret diffusion models, which we discuss.","url_abs":"https://arxiv.org/abs/2305.11089v1","url_pdf":"https://arxiv.org/pdf/2305.11089v1.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":"blackout-diffusion-generative-diffusion","repo_url":"https://github.com/lanl/blackout-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-cifar-10","task":"Image Generation","dataset":"CIFAR-10","model":"Blackout Diffusion","rank_in_archive_order":31,"of":78,"metrics":{"FID":"4.58"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-64x64","task":"Image Generation","dataset":"CelebA 64x64","model":"Blackout Diffusion","rank_in_archive_order":18,"of":39,"metrics":{"FID":"3.22"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.11089","atlas_url":"https://app.syntology.ai/?focus=2305.11089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11089"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/lanl/blackout-diffusion","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"6c419026e778dee2","entry":"get_data_inverse_scaler","repo":"lanl/blackout-diffusion","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/lanl/blackout-diffusion/blob/HEAD/datasets.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":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6c419026e778dee2"}},{"code_sha256_prefix":"346d2e6cc8b48a5d","entry":"get_data_scaler","repo":"lanl/blackout-diffusion","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/lanl/blackout-diffusion/blob/HEAD/datasets.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":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"346d2e6cc8b48a5d"}},{"code_sha256_prefix":"fd14d238ccd5f679","entry":"crop_resize","repo":"lanl/blackout-diffusion","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/lanl/blackout-diffusion/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fd14d238ccd5f679"}},{"code_sha256_prefix":"2b9c5e011b00f419","entry":"restore_checkpoint","repo":"lanl/blackout-diffusion","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lanl/blackout-diffusion/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2b9c5e011b00f419"}},{"code_sha256_prefix":"a72a700d5e6341f5","entry":"restore_checkpoint_BD","repo":"lanl/blackout-diffusion","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lanl/blackout-diffusion/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a72a700d5e6341f5"}},{"code_sha256_prefix":"516ce9c96cccd2a5","entry":"restore_checkpoint_withEval","repo":"lanl/blackout-diffusion","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lanl/blackout-diffusion/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"516ce9c96cccd2a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}