{"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/fasterdit-towards-faster-diffusion","title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","arxiv_id":"2410.10356","date":"2024-10-14","proceeding":null,"authors":["Jingfeng Yao","Wang Cheng","Wenyu Liu","Xinggang Wang"],"abstract":"Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the following issues in the training process: firstly, certain training strategies do not consistently perform well across different data. Secondly, the effectiveness of supervision at specific timesteps is limited. In response, we propose the following contributions: (1) We introduce a new perspective for interpreting the failure of the strategies. Specifically, we slightly extend the definition of Signal-to-Noise Ratio (SNR) and suggest observing the Probability Density Function (PDF) of SNR to understand the essence of the data robustness of the strategy. (2) We conduct numerous experiments and report over one hundred experimental results to empirically summarize a unified accelerating strategy from the perspective of PDF. (3) We develop a new supervision method that further accelerates the training process of DiT. Based on them, we propose FasterDiT, an exceedingly simple and practicable design strategy. With few lines of code modifications, it achieves 2.30 FID on ImageNet 256 resolution at 1000k iterations, which is comparable to DiT (2.27 FID) but 7 times faster in training.","url_abs":"https://arxiv.org/abs/2410.10356v2","url_pdf":"https://arxiv.org/pdf/2410.10356v2.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":"fasterdit-towards-faster-diffusion","repo_url":"https://github.com/hustvl/LightningDiT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"FasterDiT-XL/2","rank_in_archive_order":49,"of":94,"metrics":{"FID":"2.03"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.10356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10356"}},"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/hustvl/LightningDiT","reach":null}],"summary":{"ran":6,"unverified":4},"by_repo_kind":{"listed":{"samples":10,"ran":6,"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":"10d58a623eb5beb1","entry":"Attention","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10d58a623eb5beb1"}},{"code_sha256_prefix":"044b0ed1c2fd2514","entry":"FinalLayer","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"044b0ed1c2fd2514"}},{"code_sha256_prefix":"908133c58e4b4a36","entry":"LabelEmbedder","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"908133c58e4b4a36"}},{"code_sha256_prefix":"3777a235d6ea1491","entry":"RMSNorm","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3777a235d6ea1491"}},{"code_sha256_prefix":"39fbca475083b37f","entry":"SwiGLUFFN","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39fbca475083b37f"}},{"code_sha256_prefix":"64a16f9548e5d293","entry":"VisionRotaryEmbeddingFast","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64a16f9548e5d293"}},{"code_sha256_prefix":"4f92bf659324e8f1","entry":"LightningDiT","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f92bf659324e8f1"}},{"code_sha256_prefix":"3df6325a7d960bdc","entry":"LightningDiTBlock","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3df6325a7d960bdc"}},{"code_sha256_prefix":"8f2712b9234f6ba0","entry":"TimestepEmbedder","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f2712b9234f6ba0"}},{"code_sha256_prefix":"5ea6b9bd142d4069","entry":"modulate","repo":"hustvl/LightningDiT","repo_kind":"listed","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ea6b9bd142d4069"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}