Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning

[2505.19261] Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2505.19261 (cs) [Submitted on 25 May 2025 ( v1 ), last revised 14 Apr 2026 (this version, v2)] Title: Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning Authors: Yu Zhang , Jialei Zhou , Xinchen Li , Qi Zhang , Zhongwei Wan , Tianyu Wang , Duoqian Miao , Changwei Wang , Longbing Cao View a PDF of the paper titled Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning, by Yu Zhang and 8 other authors View PDF HTML (experimental) Abstract: Current text-to-image diffusion generation typically employs complete-text conditioning. Due to the intricate syntax, diffusion transformers (DiTs) inherently suffer from a comprehension defect of complete-text captions. One-fly complete-text input either overlooks critical semantic details or causes semantic confusion by simultaneously modeling diverse semantic primitive types. To mitigate this defect of DiTs, we propose a novel split-text conditioning framework named DiT-ST. This framework converts a complete-text caption into a split-text caption, a collection of simplified sentences, to explicitly express various semantic primitives and their interconnections. The split-text caption is then injected into different denoising stages of DiT-ST in a hierarchical and incremental manner. Specifically, DiT-ST leverages Large Language Models to parse captions, extracting diverse primitives and hierarchically sorting out and constructing these primitives into a split-text input. Moreover, we partition the diffusion denoising process according to its differential sensitivities to diverse semantic primitive types and determine the appropriate timesteps to incrementally inject tokens of diverse semantic primitive types into input tokens via cross-attention. In this way, DiT-ST enhances the representation learning of specific semantic primitive types across different stages. Extensive experiments validate the effectiveness of our proposed DiT-ST in mitigating the complete-text comprehension defect. Comments: NeurIPS 2025 Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2505.19261 [cs.CV] (or arXiv:2505.19261v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2505.19261 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yu Zhang [ view email ] [v1] Sun, 25 May 2025 18:33:05 UTC (48,234 KB) [v2] Tue, 14 Apr 2026 06:42:51 UTC (48,234 KB) Full-text links: Access Paper: View a PDF of the paper titled Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning, by Yu Zhang and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-05 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• STEPS: Scene Text Editing with Preserved Style Using Diffusion and Contrastive Style Encoding#1143237
• AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow#997715
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text\n Transformer#7110
• Embedding Prediction Helps Image Generation#1161011
• Embedding Prediction Helps Image Generation#1157551