{"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/accelerating-vision-diffusion-transformers","title":"Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints","arxiv_id":"2411.17616","date":"2024-11-26","proceeding":null,"authors":["Guanjie Chen","Xinyu Zhao","Yucheng Zhou","Xiaoye Qu","Tianlong Chen","Yu Cheng"],"abstract":"Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference. Through systematic analysis, we identify the absence of long-range feature preservation mechanisms as the root cause of unstable feature propagation and perturbation sensitivity. To this end, we propose Skip-DiT, a novel DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets. Theoretical spectral norm and visualization analysis demonstrate how LSCs stabilize feature dynamics. Skip-DiT architecture and its stabilized dynamic feature enable an efficient statical caching mechanism that reuses deep features across timesteps while updating shallow components. Extensive experiments across image and video generation tasks demonstrate that Skip-DiT achieves: (1) 4.4 times training acceleration and faster convergence, (2) 1.5-2 times inference acceleration without quality loss and high fidelity to original output, outperforming existing DiT caching methods across various quantitative metrics. Our findings establish long-skip connections as critical architectural components for training stable and efficient diffusion transformers.","url_abs":"https://arxiv.org/abs/2411.17616v3","url_pdf":"https://arxiv.org/pdf/2411.17616v3.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":"accelerating-vision-diffusion-transformers","repo_url":"https://github.com/opensparsellms/skip-dit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2411.17616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17616"}},"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/opensparsellms/skip-dit","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran_honours":1,"unverified":6},"by_repo_kind":{"official":{"samples":10,"ran":4,"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":"7b21a01ae77703a3","entry":"create_npz_from_sample_folder","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-image/sample_ddp.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-image/sample_ddp.py","link_basis":"harvester_set","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":"7b21a01ae77703a3"}},{"code_sha256_prefix":"c92c27c924b517e8","entry":"get_2d_sincos_pos_embed","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-image/models.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-image/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c92c27c924b517e8"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-image/models.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-image/models.py","link_basis":"harvester_set","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":"03310bba324ae4fb"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-video/models/utils.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-video/models/utils.py","link_basis":"harvester_set","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":"129b804760b3115f"}},{"code_sha256_prefix":"6fe195fcfd10e259","entry":"checkpoint","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-video/models/utils.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-video/models/utils.py","link_basis":"plan_row","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":"6fe195fcfd10e259"}},{"code_sha256_prefix":"6a0d5ecd441905cc","entry":"download_model","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-image/download.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-image/download.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":true,"mcp_get_code":{"code_sha256":"6a0d5ecd441905cc"}},{"code_sha256_prefix":"29947a0a94157558","entry":"find_model","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-image/download.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-image/download.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":true,"mcp_get_code":{"code_sha256":"29947a0a94157558"}},{"code_sha256_prefix":"c8dc321d086803c8","entry":"get_1d_sincos_temp_embed","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-video/models/latte.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-video/models/latte.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":"c8dc321d086803c8"}},{"code_sha256_prefix":"665d8a4e8f673a4c","entry":"get_2d_sincos_pos_embed_from_grid","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-image/models.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-image/models.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":true,"mcp_get_code":{"code_sha256":"665d8a4e8f673a4c"}},{"code_sha256_prefix":"319f00691ca1b97c","entry":"timestep_embedding","repo":"opensparsellms/skip-dit","repo_kind":"official","path":"class-to-video/models/utils.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-video/models/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":"319f00691ca1b97c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}