{"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/improved-techniques-for-training-score-based","title":"Improved Techniques for Training Score-Based Generative Models","arxiv_id":"2006.09011","date":"2020-06-16","proceeding":"NeurIPS 2020 12","authors":["Yang Song","Stefano Ermon"],"abstract":"Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization. However, existing training procedures are limited to images of low resolution (typically below 32x32), and can be unstable under some settings. We provide a new theoretical analysis of learning and sampling from score models in high dimensional spaces, explaining existing failure modes and motivating new solutions that generalize across datasets. To enhance stability, we also propose to maintain an exponential moving average of model weights. With these improvements, we can effortlessly scale score-based generative models to images with unprecedented resolutions ranging from 64x64 to 256x256. Our score-based models can generate high-fidelity samples that rival best-in-class GANs on various image datasets, including CelebA, FFHQ, and multiple LSUN categories.","url_abs":"https://arxiv.org/abs/2006.09011v2","url_pdf":"https://arxiv.org/pdf/2006.09011v2.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":"improved-techniques-for-training-score-based","repo_url":"https://github.com/ermongroup/ncsnv2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improved-techniques-for-training-score-based","repo_url":"https://github.com/AlexiaJM/AdversarialConsistentScoreMatching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"improved-techniques-for-training-score-based","repo_url":"https://github.com/SamArgt/AudioSourceSep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"improved-techniques-for-training-score-based","repo_url":"https://github.com/ermongroup/ncsn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improved-techniques-for-training-score-based","repo_url":"https://github.com/henryaddison/score_sde_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"improved-techniques-for-training-score-based","repo_url":"https://github.com/jmyoon1/adp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improved-techniques-for-training-score-based","repo_url":"https://github.com/tpresser570/Lambert-Diffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"improved-techniques-for-training-score-based","repo_url":"https://github.com/yang-song/score_sde","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improved-techniques-for-training-score-based","repo_url":"https://github.com/yang-song/score_sde_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-cifar-10","task":"Image Generation","dataset":"CIFAR-10","model":"NCSNv2","rank_in_archive_order":46,"of":78,"metrics":{"FID":"10.87"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.09011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09011"}},"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/yang-song/score_sde","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ermongroup/ncsn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ermongroup/ncsnv2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yang-song/score_sde_pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/henryaddison/score_sde_pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SamArgt/AudioSourceSep","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AlexiaJM/AdversarialConsistentScoreMatching","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jmyoon1/adp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tpresser570/Lambert-Diffusion","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{},"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":3,"samples":[{"code_sha256_prefix":"a05b1d0cf3f508b4","entry":"register_corrector","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a05b1d0cf3f508b4"}},{"code_sha256_prefix":"473066ddf62a075a","entry":"register_predictor","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"473066ddf62a075a"}},{"code_sha256_prefix":"a58facb8fe71823a","entry":"get_predictor","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a58facb8fe71823a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}