{"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/asyncdiff-parallelizing-diffusion-models-by","title":"AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising","arxiv_id":"2406.06911","date":"2024-06-11","proceeding":null,"authors":["Zigeng Chen","Xinyin Ma","Gongfan Fang","Zhenxiong Tan","Xinchao Wang"],"abstract":"Diffusion models have garnered significant interest from the community for their great generative ability across various applications. However, their typical multi-step sequential-denoising nature gives rise to high cumulative latency, thereby precluding the possibilities of parallel computation. To address this, we introduce AsyncDiff, a universal and plug-and-play acceleration scheme that enables model parallelism across multiple devices. Our approach divides the cumbersome noise prediction model into multiple components, assigning each to a different device. To break the dependency chain between these components, it transforms the conventional sequential denoising into an asynchronous process by exploiting the high similarity between hidden states in consecutive diffusion steps. Consequently, each component is facilitated to compute in parallel on separate devices. The proposed strategy significantly reduces inference latency while minimally impacting the generative quality. Specifically, for the Stable Diffusion v2.1, AsyncDiff achieves a 2.7x speedup with negligible degradation and a 4.0x speedup with only a slight reduction of 0.38 in CLIP Score, on four NVIDIA A5000 GPUs. Our experiments also demonstrate that AsyncDiff can be readily applied to video diffusion models with encouraging performances. The code is available at https://github.com/czg1225/AsyncDiff.","url_abs":"https://arxiv.org/abs/2406.06911v3","url_pdf":"https://arxiv.org/pdf/2406.06911v3.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":"asyncdiff-parallelizing-diffusion-models-by","repo_url":"https://github.com/czg1225/asyncdiff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"asyncdiff-parallelizing-diffusion-models-by","repo_url":"https://github.com/horseee/deepcache","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.06911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06911"}},"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/horseee/deepcache","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/czg1225/asyncdiff","reach":null}],"summary":{"ran":2,"ran_fixture":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1},"listed":{"samples":2,"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":"6402d576da4049f2","entry":"ModulePlugin","repo":"czg1225/asyncdiff","repo_kind":"official","path":"asyncdiff/async_sd.py","file_url":"https://github.com/czg1225/asyncdiff/blob/HEAD/asyncdiff/async_sd.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":"6402d576da4049f2"}},{"code_sha256_prefix":"8877baf50421e9c9","entry":"ResultPicker","repo":"czg1225/asyncdiff","repo_kind":"official","path":"asyncdiff/async_sd.py","file_url":"https://github.com/czg1225/asyncdiff/blob/HEAD/asyncdiff/async_sd.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":"8877baf50421e9c9"}},{"code_sha256_prefix":"5cf2067f46870f69","entry":"generalized_steps","repo":"horseee/deepcache","repo_kind":"listed","path":"experiments/ddpm/ddpm/functions/deepcache_denoising.py","file_url":"https://github.com/horseee/deepcache/blob/HEAD/experiments/ddpm/ddpm/functions/deepcache_denoising.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5cf2067f46870f69"}},{"code_sha256_prefix":"aa81d8363da10ef5","entry":"sample_from_quad_center","repo":"horseee/deepcache","repo_kind":"listed","path":"experiments/ddpm/ddpm/functions/deepcache_denoising.py","file_url":"https://github.com/horseee/deepcache/blob/HEAD/experiments/ddpm/ddpm/functions/deepcache_denoising.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa81d8363da10ef5"}},{"code_sha256_prefix":"b94b6c156a426ebd","entry":"splite_model","repo":"czg1225/asyncdiff","repo_kind":"official","path":"asyncdiff/async_sd.py","file_url":"https://github.com/czg1225/asyncdiff/blob/HEAD/asyncdiff/async_sd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b94b6c156a426ebd"}},{"code_sha256_prefix":"ff86b0398ff7ef3f","entry":"AsyncDiff","repo":"czg1225/asyncdiff","repo_kind":"official","path":"asyncdiff/async_sd.py","file_url":"https://github.com/czg1225/asyncdiff/blob/HEAD/asyncdiff/async_sd.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":"ff86b0398ff7ef3f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}