{"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/pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","arxiv_id":"2310.00426","date":"2023-09-30","proceeding":null,"authors":["Junsong Chen","Jincheng Yu","Chongjian Ge","Lewei Yao","Enze Xie","Yue Wu","Zhongdao Wang","James Kwok","Ping Luo","Huchuan Lu","Zhenguo Li"],"abstract":"The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces PIXART-$\\alpha$, a Transformer-based T2I diffusion model whose image generation quality is competitive with state-of-the-art image generators (e.g., Imagen, SDXL, and even Midjourney), reaching near-commercial application standards. Additionally, it supports high-resolution image synthesis up to 1024px resolution with low training cost, as shown in Figure 1 and 2. To achieve this goal, three core designs are proposed: (1) Training strategy decomposition: We devise three distinct training steps that separately optimize pixel dependency, text-image alignment, and image aesthetic quality; (2) Efficient T2I Transformer: We incorporate cross-attention modules into Diffusion Transformer (DiT) to inject text conditions and streamline the computation-intensive class-condition branch; (3) High-informative data: We emphasize the significance of concept density in text-image pairs and leverage a large Vision-Language model to auto-label dense pseudo-captions to assist text-image alignment learning. As a result, PIXART-$\\alpha$'s training speed markedly surpasses existing large-scale T2I models, e.g., PIXART-$\\alpha$ only takes 10.8% of Stable Diffusion v1.5's training time (675 vs. 6,250 A100 GPU days), saving nearly \\$300,000 (\\$26,000 vs. \\$320,000) and reducing 90% CO2 emissions. Moreover, compared with a larger SOTA model, RAPHAEL, our training cost is merely 1%. Extensive experiments demonstrate that PIXART-$\\alpha$ excels in image quality, artistry, and semantic control. We hope PIXART-$\\alpha$ will provide new insights to the AIGC community and startups to accelerate building their own high-quality yet low-cost generative models from scratch.","url_abs":"https://arxiv.org/abs/2310.00426v3","url_pdf":"https://arxiv.org/pdf/2310.00426v3.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":"pixart-a-fast-training-of-diffusion","repo_url":"https://github.com/PixArt-alpha/PixArt-alpha","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pixart-a-fast-training-of-diffusion","repo_url":"https://github.com/Karine-Huang/T2I-CompBench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pixart-a-fast-training-of-diffusion","repo_url":"https://github.com/swookey-thinky/image_diffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/on-wise","task":"","dataset":"WISE","model":"PixArt-Alpha","rank_in_archive_order":5,"of":11,"metrics":{"Biology":"0.49","Chemistry":"0.34","Cultural":"0.45","Overall":"0.47","Physics":"0.56","Space":"0.48","Time":"0.50"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset":"WISE","model":"PixArt-XL-2-1024-MS","rank_in_archive_order":7,"of":14,"metrics":{"Biology":"0.49","Chemistry":"0.34","Cultural":"0.45","Overall":"0.47","Physics":"0.56","Space":"0.48","Time":"0.50"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-t2i-compbench","task":"Text-to-Image Generation","dataset":"T2I-CompBench","model":"PixArt-a","rank_in_archive_order":2,"of":2,"metrics":{"Color":"0.6886","Complex":"0.4117","Non-Spatial":"0.3179","Shape":"0.5582","Spatial":"0.2082","Texture":"0.7044"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.00426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00426"}},"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/Karine-Huang/T2I-CompBench","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/swookey-thinky/image_diffusion","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PixArt-alpha/PixArt-alpha","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":2,"samples":[{"code_sha256_prefix":"e5947aba1d10885f","entry":"get_1d_sincos_pos_embed_from_grid","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"code_sha256_prefix":"a5e3d9618aac5205","entry":"t2i_modulate","repo":"swookey-thinky/image_diffusion","repo_kind":"listed","path":"image_diffusion/score_networks/pixart.py","file_url":"https://github.com/swookey-thinky/image_diffusion/blob/HEAD/image_diffusion/score_networks/pixart.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5e3d9618aac5205"}},{"code_sha256_prefix":"665d8a4e8f673a4c","entry":"get_2d_sincos_pos_embed_from_grid","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"665d8a4e8f673a4c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}