{"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/denoising-diffusion-step-aware-models","title":"Denoising Diffusion Step-aware Models","arxiv_id":"2310.03337","date":"2023-10-05","proceeding":null,"authors":["Shuai Yang","Yukang Chen","Luozhou Wang","Shu Liu","Yingcong Chen"],"abstract":"Denoising Diffusion Probabilistic Models (DDPMs) have garnered popularity for data generation across various domains. However, a significant bottleneck is the necessity for whole-network computation during every step of the generative process, leading to high computational overheads. This paper presents a novel framework, Denoising Diffusion Step-aware Models (DDSM), to address this challenge. Unlike conventional approaches, DDSM employs a spectrum of neural networks whose sizes are adapted according to the importance of each generative step, as determined through evolutionary search. This step-wise network variation effectively circumvents redundant computational efforts, particularly in less critical steps, thereby enhancing the efficiency of the diffusion model. Furthermore, the step-aware design can be seamlessly integrated with other efficiency-geared diffusion models such as DDIMs and latent diffusion, thus broadening the scope of computational savings. Empirical evaluations demonstrate that DDSM achieves computational savings of 49% for CIFAR-10, 61% for CelebA-HQ, 59% for LSUN-bedroom, 71% for AFHQ, and 76% for ImageNet, all without compromising the generation quality.","url_abs":"https://arxiv.org/abs/2310.03337v5","url_pdf":"https://arxiv.org/pdf/2310.03337v5.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":"denoising-diffusion-step-aware-models","repo_url":"https://github.com/envision-research/ddsm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.03337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03337"}},"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/envision-research/ddsm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":"cd3edab30cfead44","entry":"calculate_frechet_distance","repo":"envision-research/ddsm","repo_kind":"official","path":"score/fid.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/score/fid.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd3edab30cfead44"}},{"code_sha256_prefix":"32f1f27f7d19f6ad","entry":"conv_module_name_filter","repo":"envision-research/ddsm","repo_kind":"official","path":"profile.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/profile.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32f1f27f7d19f6ad"}},{"code_sha256_prefix":"6a78f18d5b2ce056","entry":"extract","repo":"envision-research/ddsm","repo_kind":"official","path":"diffusion.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a78f18d5b2ce056"}},{"code_sha256_prefix":"9b81ae7906ed29eb","entry":"get_inception_score","repo":"envision-research/ddsm","repo_kind":"official","path":"score/inception_score.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/score/inception_score.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b81ae7906ed29eb"}},{"code_sha256_prefix":"e2db4aa1fd031021","entry":"get_params","repo":"envision-research/ddsm","repo_kind":"official","path":"profile.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/profile.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2db4aa1fd031021"}},{"code_sha256_prefix":"e99703e8431cce45","entry":"make_divisible","repo":"envision-research/ddsm","repo_kind":"official","path":"slimmable_ops.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/slimmable_ops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e99703e8431cce45"}},{"code_sha256_prefix":"6149e2d484175e99","entry":"run_forward","repo":"envision-research/ddsm","repo_kind":"official","path":"profile.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/profile.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6149e2d484175e99"}},{"code_sha256_prefix":"b304af5c4fc5341a","entry":"torch_cov","repo":"envision-research/ddsm","repo_kind":"official","path":"score/fid.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/score/fid.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b304af5c4fc5341a"}},{"code_sha256_prefix":"0d58f98849bb68ab","entry":"get_fid_score","repo":"envision-research/ddsm","repo_kind":"official","path":"score/both.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/score/both.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":"0d58f98849bb68ab"}},{"code_sha256_prefix":"526c471ba9b04752","entry":"get_inception_and_fid_score","repo":"envision-research/ddsm","repo_kind":"official","path":"score/both.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/score/both.py","link_basis":"harvester_set","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":"526c471ba9b04752"}},{"code_sha256_prefix":"2dfa8886e774088c","entry":"sqrt_newton_schulz","repo":"envision-research/ddsm","repo_kind":"official","path":"score/fid.py","file_url":"https://github.com/envision-research/ddsm/blob/HEAD/score/fid.py","link_basis":"harvester_set","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":"2dfa8886e774088c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}