{"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/training-free-adaptive-diffusion-with-bounded","title":"Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy","arxiv_id":"2410.09873","date":"2024-10-13","proceeding":null,"authors":["Hancheng Ye","Jiakang Yuan","Renqiu Xia","Xiangchao Yan","Tao Chen","Junchi Yan","Botian Shi","Bo Zhang"],"abstract":"Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers from high computation cost, resulting in a prohibitive latency for interactive applications. In this paper, we propose AdaptiveDiffusion to relieve this bottleneck by adaptively reducing the noise prediction steps during the denoising process. Our method considers the potential of skipping as many noise prediction steps as possible while keeping the final denoised results identical to the original full-step ones. Specifically, the skipping strategy is guided by the third-order latent difference that indicates the stability between timesteps during the denoising process, which benefits the reusing of previous noise prediction results. Extensive experiments on image and video diffusion models demonstrate that our method can significantly speed up the denoising process while generating identical results to the original process, achieving up to an average 2~5x speedup without quality degradation.","url_abs":"https://arxiv.org/abs/2410.09873v1","url_pdf":"https://arxiv.org/pdf/2410.09873v1.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":"training-free-adaptive-diffusion-with-bounded","repo_url":"https://github.com/unimodal4reasoning/adaptivediffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"prediction","task_name":"Prediction"}],"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=2410.09873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09873"}},"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/unimodal4reasoning/adaptivediffusion","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_fixture":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1},"community":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"b9424de667307f8f","entry":"bytes_to_giga_bytes","repo":"unimodal4reasoning/adaptivediffusion","repo_kind":"official","path":"benchmarks/utils.py","file_url":"https://github.com/unimodal4reasoning/adaptivediffusion/blob/HEAD/benchmarks/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b9424de667307f8f"}},{"code_sha256_prefix":"565295ed162e2027","entry":"filter_float","repo":"unimodal4reasoning/adaptivediffusion","repo_kind":"official","path":"benchmarks/push_results.py","file_url":"https://github.com/unimodal4reasoning/adaptivediffusion/blob/HEAD/benchmarks/push_results.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"565295ed162e2027"}},{"code_sha256_prefix":"3ee5b3663f749813","entry":"get_timestep_embedding","repo":"horseee/deepcache","repo_kind":"community","path":"experiments/ddpm/ddpm/models/deepcache_diffusion.py","file_url":"https://github.com/horseee/deepcache/blob/HEAD/experiments/ddpm/ddpm/models/deepcache_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ee5b3663f749813"}},{"code_sha256_prefix":"34fb5c76abd4dae8","entry":"nonlinearity","repo":"horseee/deepcache","repo_kind":"community","path":"experiments/ddpm/ddpm/models/deepcache_diffusion.py","file_url":"https://github.com/horseee/deepcache/blob/HEAD/experiments/ddpm/ddpm/models/deepcache_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34fb5c76abd4dae8"}},{"code_sha256_prefix":"caf44b9a51fc258f","entry":"run_command","repo":"unimodal4reasoning/adaptivediffusion","repo_kind":"official","path":"benchmarks/run_all.py","file_url":"https://github.com/unimodal4reasoning/adaptivediffusion/blob/HEAD/benchmarks/run_all.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"caf44b9a51fc258f"}},{"code_sha256_prefix":"4a2c147231aea71b","entry":"Normalize","repo":"horseee/deepcache","repo_kind":"community","path":"experiments/ddpm/ddpm/models/deepcache_diffusion.py","file_url":"https://github.com/horseee/deepcache/blob/HEAD/experiments/ddpm/ddpm/models/deepcache_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a2c147231aea71b"}},{"code_sha256_prefix":"96ba9b82cde84ba4","entry":"benchmark_fn","repo":"unimodal4reasoning/adaptivediffusion","repo_kind":"official","path":"benchmarks/utils.py","file_url":"https://github.com/unimodal4reasoning/adaptivediffusion/blob/HEAD/benchmarks/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96ba9b82cde84ba4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}