{"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/from-reusing-to-forecasting-accelerating","title":"From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers","arxiv_id":"2503.06923","date":"2025-03-10","proceeding":null,"authors":["Jiacheng Liu","Chang Zou","Yuanhuiyi Lyu","Junjie Chen","Linfeng Zhang"],"abstract":"Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. To solve this problem, feature caching has been proposed to accelerate diffusion models by caching the features in the previous timesteps and then reusing them in the following timesteps. However, at timesteps with significant intervals, the feature similarity in diffusion models decreases substantially, leading to a pronounced increase in errors introduced by feature caching, significantly harming the generation quality. To solve this problem, we propose TaylorSeer, which firstly shows that features of diffusion models at future timesteps can be predicted based on their values at previous timesteps. Based on the fact that features change slowly and continuously across timesteps, TaylorSeer employs a differential method to approximate the higher-order derivatives of features and predict features in future timesteps with Taylor series expansion. Extensive experiments demonstrate its significant effectiveness in both image and video synthesis, especially in high acceleration ratios. For instance, it achieves an almost lossless acceleration of 4.99$\\times$ on FLUX and 5.00$\\times$ on HunyuanVideo without additional training. On DiT, it achieves $3.41$ lower FID compared with previous SOTA at $4.53$$\\times$ acceleration. %Our code is provided in the supplementary materials and will be made publicly available on GitHub. Our codes have been released in Github:https://github.com/Shenyi-Z/TaylorSeer","url_abs":"https://arxiv.org/abs/2503.06923v1","url_pdf":"https://arxiv.org/pdf/2503.06923v1.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":"from-reusing-to-forecasting-accelerating","repo_url":"https://github.com/Shenyi-Z/TaylorSeer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"from-reusing-to-forecasting-accelerating","repo_url":"https://github.com/Shenyi-Z/ToCa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.06923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06923"}},"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/Shenyi-Z/ToCa","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Shenyi-Z/TaylorSeer","reach":null}],"summary":{"ran":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"7b710ca7cb2fb484","entry":"fresh_ratio_scheduler","repo":"Shenyi-Z/ToCa","repo_kind":"listed","path":"DiT-ToCa/cache_functions/cache_cutfresh.py","file_url":"https://github.com/Shenyi-Z/ToCa/blob/HEAD/DiT-ToCa/cache_functions/cache_cutfresh.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7b710ca7cb2fb484"}},{"code_sha256_prefix":"bad09b4442e43962","entry":"local_selection_with_bonus","repo":"Shenyi-Z/ToCa","repo_kind":"listed","path":"DiT-ToCa/cache_functions/cache_cutfresh.py","file_url":"https://github.com/Shenyi-Z/ToCa/blob/HEAD/DiT-ToCa/cache_functions/cache_cutfresh.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"bad09b4442e43962"}},{"code_sha256_prefix":"bcf024e31fd32610","entry":"cache_cutfresh","repo":"Shenyi-Z/ToCa","repo_kind":"listed","path":"DiT-ToCa/cache_functions/cache_cutfresh.py","file_url":"https://github.com/Shenyi-Z/ToCa/blob/HEAD/DiT-ToCa/cache_functions/cache_cutfresh.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"bcf024e31fd32610"}},{"code_sha256_prefix":"fa84af6f1f540aa1","entry":"score_evaluate","repo":"Shenyi-Z/ToCa","repo_kind":"listed","path":"DiT-ToCa/cache_functions/cache_cutfresh.py","file_url":"https://github.com/Shenyi-Z/ToCa/blob/HEAD/DiT-ToCa/cache_functions/cache_cutfresh.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fa84af6f1f540aa1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}