{"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-s-weak-to-strong-training-of-diffusion","title":"PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","arxiv_id":"2403.04692","date":"2024-03-07","proceeding":null,"authors":["Junsong Chen","Chongjian Ge","Enze Xie","Yue Wu","Lewei Yao","Xiaozhe Ren","Zhongdao Wang","Ping Luo","Huchuan Lu","Zhenguo Li"],"abstract":"In this paper, we introduce PixArt-\\Sigma, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-\\Sigma represents a significant advancement over its predecessor, PixArt-\\alpha, offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of PixArt-\\Sigma is its training efficiency. Leveraging the foundational pre-training of PixArt-\\alpha, it evolves from the `weaker' baseline to a `stronger' model via incorporating higher quality data, a process we term \"weak-to-strong training\". The advancements in PixArt-\\Sigma are twofold: (1) High-Quality Training Data: PixArt-\\Sigma incorporates superior-quality image data, paired with more precise and detailed image captions. (2) Efficient Token Compression: we propose a novel attention module within the DiT framework that compresses both keys and values, significantly improving efficiency and facilitating ultra-high-resolution image generation. Thanks to these improvements, PixArt-\\Sigma achieves superior image quality and user prompt adherence capabilities with significantly smaller model size (0.6B parameters) than existing text-to-image diffusion models, such as SDXL (2.6B parameters) and SD Cascade (5.1B parameters). Moreover, PixArt-\\Sigma's capability to generate 4K images supports the creation of high-resolution posters and wallpapers, efficiently bolstering the production of high-quality visual content in industries such as film and gaming.","url_abs":"https://arxiv.org/abs/2403.04692v2","url_pdf":"https://arxiv.org/pdf/2403.04692v2.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-s-weak-to-strong-training-of-diffusion","repo_url":"https://github.com/PixArt-alpha/PixArt-sigma","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pixart-s-weak-to-strong-training-of-diffusion","repo_url":"https://github.com/mindspore-lab/mindone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"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":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-textatlaseval","task":"Image Generation","dataset":"TextAtlasEval","model":"PixArt-Sigma","rank_in_archive_order":5,"of":7,"metrics":{"StyledTextSynth Clip Score":"0.2764","StyledTextSynth FID":"82.83","StyledTextSynth OCR (Accuracy)":"0.42","StyledTextSynth OCR (Cer)":"0.90","StyledTextSynth OCR (F1 Score)":"0.62","TextScenesHQ Clip Score":"0.2347","TextScenesHQ FID":"72.62","TextScenesHQ OCR (Accuracy)":"0.34","TextScenesHQ OCR (Cer)":"0.91","TextScenesHQ OCR (F1 Score)":"0.53","TextVisionBlend Clip Score":"0.1891","TextVisionBlend FID":"81.29","TextVisionBlend OCR (Accuracy)":"2.40","TextVisionBlend OCR (Cer)":"0.83","TextVsionBlend OCR (F1 Score)":"1.57"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-geneval","task":"Text-to-Image Generation","dataset":"GenEval","model":"PixArt-Σ","rank_in_archive_order":18,"of":20,"metrics":{"Overall":"0.53"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.04692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04692"}},"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/PixArt-alpha/PixArt-sigma","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-lab/mindone","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran_fixture":2,"ran":2,"ran_draft_wrong":1,"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"30befb7e4327e615","entry":"append_dims","repo":"PixArt-alpha/PixArt-sigma","repo_kind":"official","path":"train_scripts/train_pixart_lcm.py","file_url":"https://github.com/PixArt-alpha/PixArt-sigma/blob/HEAD/train_scripts/train_pixart_lcm.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"30befb7e4327e615"}},{"code_sha256_prefix":"652bf9fefb65310b","entry":"apply_style","repo":"PixArt-alpha/PixArt-sigma","repo_kind":"official","path":"app/app_pixart_sigma.py","file_url":"https://github.com/PixArt-alpha/PixArt-sigma/blob/HEAD/app/app_pixart_sigma.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":"652bf9fefb65310b"}},{"code_sha256_prefix":"a15cfd7932844ef9","entry":"extract_into_tensor","repo":"PixArt-alpha/PixArt-sigma","repo_kind":"official","path":"train_scripts/train_pixart_lcm.py","file_url":"https://github.com/PixArt-alpha/PixArt-sigma/blob/HEAD/train_scripts/train_pixart_lcm.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a15cfd7932844ef9"}},{"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":"1c00f3d9c2aa103c","entry":"randomize_seed_fn","repo":"PixArt-alpha/PixArt-sigma","repo_kind":"official","path":"app/app_pixart_sigma.py","file_url":"https://github.com/PixArt-alpha/PixArt-sigma/blob/HEAD/app/app_pixart_sigma.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":true,"mcp_get_code":{"code_sha256":"1c00f3d9c2aa103c"}},{"code_sha256_prefix":"bf8e9418920783fb","entry":"scalings_for_boundary_conditions","repo":"PixArt-alpha/PixArt-sigma","repo_kind":"official","path":"train_scripts/train_pixart_lcm.py","file_url":"https://github.com/PixArt-alpha/PixArt-sigma/blob/HEAD/train_scripts/train_pixart_lcm.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bf8e9418920783fb"}},{"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"}},{"code_sha256_prefix":"168a4054b9fdff36","entry":"onestep_sampler","repo":"PixArt-alpha/PixArt-sigma","repo_kind":"official","path":"train_scripts/train_pixart_dmd.py","file_url":"https://github.com/PixArt-alpha/PixArt-sigma/blob/HEAD/train_scripts/train_pixart_dmd.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":"168a4054b9fdff36"}},{"code_sha256_prefix":"b5d5cc55585820d9","entry":"save_image","repo":"PixArt-alpha/PixArt-sigma","repo_kind":"official","path":"app/app_pixart_sigma.py","file_url":"https://github.com/PixArt-alpha/PixArt-sigma/blob/HEAD/app/app_pixart_sigma.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":"b5d5cc55585820d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}