{"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/restart-sampling-for-improving-generative","title":"Restart Sampling for Improving Generative Processes","arxiv_id":"2306.14878","date":"2023-06-26","proceeding":"NeurIPS 2023 11","authors":["Yilun Xu","Mingyang Deng","Xiang Cheng","Yonglong Tian","Ziming Liu","Tommi Jaakkola"],"abstract":"Generative processes that involve solving differential equations, such as diffusion models, frequently necessitate balancing speed and quality. ODE-based samplers are fast but plateau in performance while SDE-based samplers deliver higher sample quality at the cost of increased sampling time. We attribute this difference to sampling errors: ODE-samplers involve smaller discretization errors while stochasticity in SDE contracts accumulated errors. Based on these findings, we propose a novel sampling algorithm called Restart in order to better balance discretization errors and contraction. The sampling method alternates between adding substantial noise in additional forward steps and strictly following a backward ODE. Empirically, Restart sampler surpasses previous SDE and ODE samplers in both speed and accuracy. Restart not only outperforms the previous best SDE results, but also accelerates the sampling speed by 10-fold / 2-fold on CIFAR-10 / ImageNet $64 \\times 64$. In addition, it attains significantly better sample quality than ODE samplers within comparable sampling times. Moreover, Restart better balances text-image alignment/visual quality versus diversity than previous samplers in the large-scale text-to-image Stable Diffusion model pre-trained on LAION $512 \\times 512$. Code is available at https://github.com/Newbeeer/diffusion_restart_sampling","url_abs":"https://arxiv.org/abs/2306.14878v2","url_pdf":"https://arxiv.org/pdf/2306.14878v2.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":"restart-sampling-for-improving-generative","repo_url":"https://github.com/newbeeer/diffusion_restart_sampling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok"}},{"paper_slug":"restart-sampling-for-improving-generative","repo_url":"https://github.com/carzit/sd-webui-samplers-scheduler","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.14878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.14878"}},"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/newbeeer/diffusion_restart_sampling","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/carzit/sd-webui-samplers-scheduler","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"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":1,"samples":[{"code_sha256_prefix":"cacd4f6ec202d9b4","entry":"parse_int_list","repo":"newbeeer/diffusion_restart_sampling","repo_kind":"official","path":"benchmarks/generate_restart.py","file_url":"https://github.com/newbeeer/diffusion_restart_sampling/blob/HEAD/benchmarks/generate_restart.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cacd4f6ec202d9b4"}},{"code_sha256_prefix":"5ce385ec63872c02","entry":"split_sigmas","repo":"carzit/sd-webui-samplers-scheduler","repo_kind":"listed","path":"Seniorious.py","file_url":"https://github.com/carzit/sd-webui-samplers-scheduler/blob/HEAD/Seniorious.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ce385ec63872c02"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}