{"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/sana-sprint-one-step-diffusion-with","title":"SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation","arxiv_id":"2503.09641","date":"2025-03-12","proceeding":null,"authors":["Junsong Chen","Shuchen Xue","Yuyang Zhao","Jincheng Yu","Sayak Paul","Junyu Chen","Han Cai","Song Han","Enze Xie"],"abstract":"This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference steps from 20 to 1-4. We introduce three key innovations: (1) We propose a training-free approach that transforms a pre-trained flow-matching model for continuous-time consistency distillation (sCM), eliminating costly training from scratch and achieving high training efficiency. Our hybrid distillation strategy combines sCM with latent adversarial distillation (LADD): sCM ensures alignment with the teacher model, while LADD enhances single-step generation fidelity. (2) SANA-Sprint is a unified step-adaptive model that achieves high-quality generation in 1-4 steps, eliminating step-specific training and improving efficiency. (3) We integrate ControlNet with SANA-Sprint for real-time interactive image generation, enabling instant visual feedback for user interaction. SANA-Sprint establishes a new Pareto frontier in speed-quality tradeoffs, achieving state-of-the-art performance with 7.59 FID and 0.74 GenEval in only 1 step - outperforming FLUX-schnell (7.94 FID / 0.71 GenEval) while being 10x faster (0.1s vs 1.1s on H100). It also achieves 0.1s (T2I) and 0.25s (ControlNet) latency for 1024 x 1024 images on H100, and 0.31s (T2I) on an RTX 4090, showcasing its exceptional efficiency and potential for AI-powered consumer applications (AIPC). Code and pre-trained models will be open-sourced.","url_abs":"https://arxiv.org/abs/2503.09641v3","url_pdf":"https://arxiv.org/pdf/2503.09641v3.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"sana-sprint-one-step-diffusion-with","repo_url":"https://github.com/NVlabs/Sana","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.09641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09641"}},"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/NVlabs/Sana","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":11},"by_repo_kind":{"official":{"samples":12,"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":12,"samples":[{"code_sha256_prefix":"1c00f3d9c2aa103c","entry":"randomize_seed_fn","repo":"NVlabs/Sana","repo_kind":"official","path":"app/app_sana_4bit.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/app_sana_4bit.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1c00f3d9c2aa103c"}},{"code_sha256_prefix":"2b6d6883dc96127d","entry":"apply_style","repo":"NVlabs/Sana","repo_kind":"official","path":"app/app_sana.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/app_sana.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2b6d6883dc96127d"}},{"code_sha256_prefix":"9d06ee4c83d30c78","entry":"classify_height_width_bin","repo":"NVlabs/Sana","repo_kind":"official","path":"app/sana_controlnet_pipeline.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/sana_controlnet_pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9d06ee4c83d30c78"}},{"code_sha256_prefix":"a21b14671ce99511","entry":"extract_greyscale_mask","repo":"NVlabs/Sana","repo_kind":"official","path":"app/app_sana_inpaint.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/app_sana_inpaint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a21b14671ce99511"}},{"code_sha256_prefix":"4d4ea6fb407e109b","entry":"get_ar_from_ref_image","repo":"NVlabs/Sana","repo_kind":"official","path":"app/sana_controlnet_pipeline.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/sana_controlnet_pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4d4ea6fb407e109b"}},{"code_sha256_prefix":"57e4b02c63e00263","entry":"guidance_type_select","repo":"NVlabs/Sana","repo_kind":"official","path":"app/sana_controlnet_pipeline.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/sana_controlnet_pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"57e4b02c63e00263"}},{"code_sha256_prefix":"34bc01284508eb93","entry":"hash_str_to_int","repo":"NVlabs/Sana","repo_kind":"official","path":"app/app_sana_4bit_compare_bf16.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/app_sana_4bit_compare_bf16.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"34bc01284508eb93"}},{"code_sha256_prefix":"b3da9990e1ba94e2","entry":"norm_ip","repo":"NVlabs/Sana","repo_kind":"official","path":"app/app_sana_controlnet_hed.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/app_sana_controlnet_hed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b3da9990e1ba94e2"}},{"code_sha256_prefix":"3766af1242aa1f12","entry":"run_inference","repo":"NVlabs/Sana","repo_kind":"official","path":"app/app_sana.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/app_sana.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3766af1242aa1f12"}},{"code_sha256_prefix":"3b9d90947aa40dd2","entry":"save_image","repo":"NVlabs/Sana","repo_kind":"official","path":"app/app_sana_controlnet_hed.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/app_sana_controlnet_hed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3b9d90947aa40dd2"}},{"code_sha256_prefix":"ec6eb00169f04a34","entry":"save_image_sana","repo":"NVlabs/Sana","repo_kind":"official","path":"app/app_sana_4bit.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/app_sana_4bit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ec6eb00169f04a34"}},{"code_sha256_prefix":"01b02ff9e21d4414","entry":"tensor_to_pil","repo":"NVlabs/Sana","repo_kind":"official","path":"app/sana_pipeline_inpaint.py","file_url":"https://github.com/NVlabs/Sana/blob/HEAD/app/sana_pipeline_inpaint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"01b02ff9e21d4414"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}