{"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/one-step-diffusion-via-shortcut-models","title":"One Step Diffusion via Shortcut Models","arxiv_id":"2410.12557","date":"2024-10-16","proceeding":null,"authors":["Kevin Frans","Danijar Hafner","Sergey Levine","Pieter Abbeel"],"abstract":"Diffusion models and flow-matching models have enabled generating diverse and realistic images by learning to transfer noise to data. However, sampling from these models involves iterative denoising over many neural network passes, making generation slow and expensive. Previous approaches for speeding up sampling require complex training regimes, such as multiple training phases, multiple networks, or fragile scheduling. We introduce shortcut models, a family of generative models that use a single network and training phase to produce high-quality samples in a single or multiple sampling steps. Shortcut models condition the network not only on the current noise level but also on the desired step size, allowing the model to skip ahead in the generation process. Across a wide range of sampling step budgets, shortcut models consistently produce higher quality samples than previous approaches, such as consistency models and reflow. Compared to distillation, shortcut models reduce complexity to a single network and training phase and additionally allow varying step budgets at inference time.","url_abs":"https://arxiv.org/abs/2410.12557v1","url_pdf":"https://arxiv.org/pdf/2410.12557v1.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":"one-step-diffusion-via-shortcut-models","repo_url":"https://github.com/kvfrans/shortcut-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"one-step-diffusion-via-shortcut-models","repo_url":"https://github.com/leffff/FlowModels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"scheduling","task_name":"Scheduling"}],"methods":[{"method_slug":"cm","method_name":"Consistency Models"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.12557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12557"}},"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/kvfrans/shortcut-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leffff/FlowModels","reach":null}],"summary":{"ran_draft_wrong":3,"ran_violates":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":3,"ran":3,"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":"950ef8f57521a359","entry":"generate","repo":"leffff/FlowModels","repo_kind":"listed","path":"flow_models/generation.py","file_url":"https://github.com/leffff/FlowModels/blob/HEAD/flow_models/generation.py","link_basis":"first_harvest_node","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":"950ef8f57521a359"}},{"code_sha256_prefix":"308823fac3064b2c","entry":"generate_euler","repo":"leffff/FlowModels","repo_kind":"listed","path":"flow_models/generation.py","file_url":"https://github.com/leffff/FlowModels/blob/HEAD/flow_models/generation.py","link_basis":"first_harvest_node","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":"308823fac3064b2c"}},{"code_sha256_prefix":"3c249ceb7aed3145","entry":"generate_midpoint","repo":"leffff/FlowModels","repo_kind":"listed","path":"flow_models/generation.py","file_url":"https://github.com/leffff/FlowModels/blob/HEAD/flow_models/generation.py","link_basis":"first_harvest_node","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":"3c249ceb7aed3145"}},{"code_sha256_prefix":"8bc124524abd3bbc","entry":"modulate","repo":"kvfrans/shortcut-models","repo_kind":"official","path":"model.py","file_url":"https://github.com/kvfrans/shortcut-models/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bc124524abd3bbc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}