# MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model Source: [MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model]() Collection index: [llms.txt]() Data updated: 2026-04-08T05:00:04.658Z Authors: Quan Dao, Dimitris Metaxas Published: 2026-03-27T12:30:10.000Z ## Abstract Transformer architectures, particularly Diffusion Transformers (DiTs), have become widely used in diffusion and flow-matching models due to their strong performance compared to convolutional UNets. However, the isotropic design of DiTs processes the same number of patchified tokens in every block, leading to relatively heavy computation during training process. In this work, we introduce a multi-patch transformer design in which early blocks operate on larger patches to capture coarse global context, while later blocks use smaller patches to refine local details. This hierarchical design could reduces computational cost by up to 50% in GFLOPs while achieving good generative performance. In addition, we also propose improved designs for time and class embeddings that accelerate training convergence. Extensive experiments on the ImageNet dataset demonstrate the effectiveness of our architectural choices. Code is released at: https://github.com/quandao10/MPDiT ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Class-conditional Image Generation on ImageNet 512x512](): Class-conditional Image Generation; ImageNet 512x512; FID: 2.47. - [Class-conditional Image Generation on ImageNet 256x256](): Class-conditional Image Generation; ImageNet 256x256; Inception Score (IS): 278.73. ## Original sources and implementation [Original paper]() [PDF]()