Recent advancements in text-to-image (T2I) generation have led to the emergence of highly expressive models such as diffusion transformers (DiTs), exemplified by FLUX. However, their massive parameter sizes lead to slow inference, high memory usage, and poor deployability. Existing acceleration methods (e.g., single-step distillation and attention pruning) often suffer from significant performance degradation and incur substantial training costs. To address these limitations, we propose FastFLUX, an architecture-level pruning framework designed to enhance the inference efficiency of FLUX. At its core is the Block-wise Replacement with Linear Layers (BRLL) method, which replaces structurally complex residual branches in ResBlocks with lightweight linear layers while preserving the original shortcut connections for stability. Furthermore, we introduce Sandwich Training (ST), a localized fine-tuning strategy that leverages LoRA to supervise neighboring blocks, mitigating performance drops caused by structural replacement. Experiments show that our FastFLUX maintains high image quality under both qualitative and quantitative evaluations, while significantly improving inference speed, even with 20\% of the hierarchy pruned. Our code will be available soon.

翻译：近年来，文本到图像生成技术取得了显著进展，催生了以FLUX为代表的、具有高度表现力的扩散Transformer模型。然而，这些模型参数量巨大，导致推理速度慢、内存占用高、部署性差。现有的加速方法（如单步蒸馏和注意力剪枝）通常存在显著的性能下降问题，且训练成本高昂。为应对这些挑战，我们提出了FastFLUX，一种架构层面的剪枝框架，旨在提升FLUX的推理效率。其核心是块级线性层替换方法，该方法将ResBlock中结构复杂的残差分支替换为轻量级的线性层，同时保留原有的快捷连接以确保稳定性。此外，我们引入了三明治训练，一种基于LoRA的局部微调策略，通过监督相邻模块来缓解结构替换导致的性能下降。实验表明，即使在层级剪枝20%的情况下，FastFLUX在定性和定量评估中均能保持较高的图像生成质量，同时显著提升了推理速度。代码即将开源。