{"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-distillation-through-score","title":"One-Step Diffusion Distillation through Score Implicit Matching","arxiv_id":"2410.16794","date":"2024-10-22","proceeding":null,"authors":["Weijian Luo","Zemin Huang","Zhengyang Geng","J. Zico Kolter","Guo-Jun Qi"],"abstract":"Despite their strong performances on many generative tasks, diffusion models require a large number of sampling steps in order to generate realistic samples. This has motivated the community to develop effective methods to distill pre-trained diffusion models into more efficient models, but these methods still typically require few-step inference or perform substantially worse than the underlying model. In this paper, we present Score Implicit Matching (SIM) a new approach to distilling pre-trained diffusion models into single-step generator models, while maintaining almost the same sample generation ability as the original model as well as being data-free with no need of training samples for distillation. The method rests upon the fact that, although the traditional score-based loss is intractable to minimize for generator models, under certain conditions we can efficiently compute the gradients for a wide class of score-based divergences between a diffusion model and a generator. SIM shows strong empirical performances for one-step generators: on the CIFAR10 dataset, it achieves an FID of 2.06 for unconditional generation and 1.96 for class-conditional generation. Moreover, by applying SIM to a leading transformer-based diffusion model, we distill a single-step generator for text-to-image (T2I) generation that attains an aesthetic score of 6.42 with no performance decline over the original multi-step counterpart, clearly outperforming the other one-step generators including SDXL-TURBO of 5.33, SDXL-LIGHTNING of 5.34 and HYPER-SDXL of 5.85. We will release this industry-ready one-step transformer-based T2I generator along with this paper.","url_abs":"https://arxiv.org/abs/2410.16794v1","url_pdf":"https://arxiv.org/pdf/2410.16794v1.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-distillation-through-score","repo_url":"https://github.com/maple-research-lab/sim","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"one-step-diffusion-distillation-through-score","repo_url":"https://github.com/pkulwj1994/diff_instruct_star","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.16794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16794"}},"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/pkulwj1994/diff_instruct_star","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maple-research-lab/sim","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"0023abc199a5c03e","entry":"generate","repo":"maple-research-lab/sim","repo_kind":"official","path":"inference.py","file_url":"https://github.com/maple-research-lab/sim/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0023abc199a5c03e"}},{"code_sha256_prefix":"c36f2a890e7ba2d6","entry":"get_2d_sincos_pos_embed","repo":"maple-research-lab/sim","repo_kind":"official","path":"models/PixArt.py","file_url":"https://github.com/maple-research-lab/sim/blob/HEAD/models/PixArt.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":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c36f2a890e7ba2d6"}},{"code_sha256_prefix":"6145c230ae09fcaf","entry":"module_forward","repo":"maple-research-lab/sim","repo_kind":"official","path":"models/PixArt.py","file_url":"https://github.com/maple-research-lab/sim/blob/HEAD/models/PixArt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6145c230ae09fcaf"}},{"code_sha256_prefix":"60599713933af278","entry":"get_2d_sincos_pos_embed_from_grid","repo":"maple-research-lab/sim","repo_kind":"official","path":"models/PixArt.py","file_url":"https://github.com/maple-research-lab/sim/blob/HEAD/models/PixArt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"60599713933af278"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}