{"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/gddim-generalized-denoising-diffusion","title":"gDDIM: Generalized denoising diffusion implicit models","arxiv_id":"2206.05564","date":"2022-06-11","proceeding":null,"authors":["Qinsheng Zhang","Molei Tao","Yongxin Chen"],"abstract":"Our goal is to extend the denoising diffusion implicit model (DDIM) to general diffusion models~(DMs) besides isotropic diffusions. Instead of constructing a non-Markov noising process as in the original DDIM, we examine the mechanism of DDIM from a numerical perspective. We discover that the DDIM can be obtained by using some specific approximations of the score when solving the corresponding stochastic differential equation. We present an interpretation of the accelerating effects of DDIM that also explains the advantages of a deterministic sampling scheme over the stochastic one for fast sampling. Building on this insight, we extend DDIM to general DMs, coined generalized DDIM (gDDIM), with a small but delicate modification in parameterizing the score network. We validate gDDIM in two non-isotropic DMs: Blurring diffusion model (BDM) and Critically-damped Langevin diffusion model (CLD). We observe more than 20 times acceleration in BDM. In the CLD, a diffusion model by augmenting the diffusion process with velocity, our algorithm achieves an FID score of 2.26, on CIFAR10, with only 50 number of score function evaluations~(NFEs) and an FID score of 2.86 with only 27 NFEs. Code is available at https://github.com/qsh-zh/gDDIM","url_abs":"https://arxiv.org/abs/2206.05564v2","url_pdf":"https://arxiv.org/pdf/2206.05564v2.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":"gddim-generalized-denoising-diffusion","repo_url":"https://github.com/qsh-zh/gDDIM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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=2206.05564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05564"}},"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/qsh-zh/gDDIM","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"unverified":11},"by_repo_kind":{"official":{"samples":13,"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":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/datasets.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c419026e778dee2"}},{"code_sha256_prefix":"346d2e6cc8b48a5d","entry":"get_data_scaler","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/datasets.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"346d2e6cc8b48a5d"}},{"code_sha256_prefix":"54a00db9aadf092f","entry":"classifier_fn_from_tfhub","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/evaluation.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"54a00db9aadf092f"}},{"code_sha256_prefix":"fd14d238ccd5f679","entry":"crop_resize","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/datasets.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fd14d238ccd5f679"}},{"code_sha256_prefix":"f537ef3271967db2","entry":"default_init","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/models/layers.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/models/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f537ef3271967db2"}},{"code_sha256_prefix":"d513609dfe366c7a","entry":"get_act","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/models/layers.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/models/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d513609dfe366c7a"}},{"code_sha256_prefix":"0799e47f0b8f6e3f","entry":"get_eps_coef_worker_fn","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/deis.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/deis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0799e47f0b8f6e3f"}},{"code_sha256_prefix":"bc1b60776e93f98c","entry":"get_normalization","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/models/normalization.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/models/normalization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc1b60776e93f98c"}},{"code_sha256_prefix":"a62e3de255f21e59","entry":"get_optimizer","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/losses.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a62e3de255f21e59"}},{"code_sha256_prefix":"0565e49d381b2ef0","entry":"ncsn_conv1x1","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/models/layers.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/models/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0565e49d381b2ef0"}},{"code_sha256_prefix":"562a245a3880c52b","entry":"optimization_manager","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/losses.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"562a245a3880c52b"}},{"code_sha256_prefix":"a60d8113b6861b0e","entry":"runge_kutta","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/deis.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/deis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a60d8113b6861b0e"}},{"code_sha256_prefix":"dc3aa97fa4491cac","entry":"single_poly_coef","repo":"qsh-zh/gDDIM","repo_kind":"official","path":"blur_jax/deis.py","file_url":"https://github.com/qsh-zh/gDDIM/blob/HEAD/blur_jax/deis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc3aa97fa4491cac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}