{"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/efficient-diffusion-training-via-min-snr","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","arxiv_id":"2303.09556","date":"2023-03-16","proceeding":"ICCV 2023 1","authors":["Tiankai Hang","Shuyang Gu","Chen Li","Jianmin Bao","Dong Chen","Han Hu","Xin Geng","Baining Guo"],"abstract":"Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting optimization directions between timesteps. To address this issue, we treat the diffusion training as a multi-task learning problem, and introduce a simple yet effective approach referred to as Min-SNR-$\\gamma$. This method adapts loss weights of timesteps based on clamped signal-to-noise ratios, which effectively balances the conflicts among timesteps. Our results demonstrate a significant improvement in converging speed, 3.4$\\times$ faster than previous weighting strategies. It is also more effective, achieving a new record FID score of 2.06 on the ImageNet $256\\times256$ benchmark using smaller architectures than that employed in previous state-of-the-art. The code is available at https://github.com/TiankaiHang/Min-SNR-Diffusion-Training.","url_abs":"https://arxiv.org/abs/2303.09556v3","url_pdf":"https://arxiv.org/pdf/2303.09556v3.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":"efficient-diffusion-training-via-min-snr","repo_url":"https://github.com/tiankaihang/min-snr-diffusion-training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"efficient-diffusion-training-via-min-snr","repo_url":"https://github.com/gohyojun15/ANT_diffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"unconditional-image-generation","task_name":"Unconditional Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"ViT-XL/2 with limited Interval Guidance","rank_in_archive_order":26,"of":94,"metrics":{"FID":"1.57"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.09556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09556"}},"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/gohyojun15/ANT_diffusion","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tiankaihang/min-snr-diffusion-training","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/TiankaiHang/Min-SNR-Diffusion-Training","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_honours":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"fa87f41839c33df3","entry":"GaussianDiffusion","repo":"gohyojun15/ANT_diffusion","repo_kind":"listed","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/gohyojun15/ANT_diffusion/blob/HEAD/diffusion/gaussian_diffusion.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":"fa87f41839c33df3"}},{"code_sha256_prefix":"2ab2316ac6fdd869","entry":"betas_for_alpha_bar","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2ab2316ac6fdd869"}},{"code_sha256_prefix":"66663f07c2ff1d4c","entry":"get_snr","repo":"TiankaiHang/Min-SNR-Diffusion-Training","repo_kind":"official","path":"guided_diffusion/gaussian_diffusion.py","file_url":"https://github.com/TiankaiHang/Min-SNR-Diffusion-Training/blob/HEAD/guided_diffusion/gaussian_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66663f07c2ff1d4c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}