PathSelect: Dynamic Token Condensation and Hierarchical Attention for Accelerated T2I Diffusion
Open Access
- 13 January 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (2) , 342
Abstract
Recent advancements in large language models (LLMs) have significantly improved text-to-image (T2I) generation, enabling systems to produce visually compelling and semantically meaningful images. However, preserving fine-grained semantic consistency in generated images, particularly in response to complex and region-specific textual prompts, remains a key challenge. In this work, we propose a context-aware hierarchical agent mechanism that integrates a semantic condensation strategy to enhance attention efficiency and maintain critical visual-textual alignment. By dynamically fusing contextual information, the method effectively balances computational efficiency and ensures semantic alignment with textual descriptions. Experimental results demonstrate improved visual coherence and semantic consistency across diverse prompts, validated through quantitative metrics and qualitative analysis. Our contributions include: (i) introducing a novel semantic condensation strategy that enhances attention efficiency while preserving critical feature information; (ii) developing a new hierarchical agent attention mechanism to enhance computation efficiency; (iii) designing an iterative feedback method based on CLIP Score to improve image diversity and overall quality.Keywords
Funding Information
- National Natural Science Foundation of China (62476216)
- University Engineering Research Center Project (24JR110)
This publication has 18 references indexed in Scilit:
- PIXART-$\Sigma $: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation2024
- Show-o: One Single Transformer to Unify Multimodal Understanding and GenerationarXiv, 2024
- The Llama 3 Herd of ModelsarXiv, 2024
- SDXL-Lightning: Progressive Adversarial Diffusion DistillationarXiv, 2024
- Divide & Bind Your Attention for Improved Generative Semantic NursingarXiv, 2023
- Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion ModelsACM Transactions on Graphics, 2023
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisarXiv, 2023
- GPT-4 Technical ReportarXiv, 2023
- Compositional Visual Generation with Composable Diffusion Models2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022