{"ID":2883477,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07519","arxiv_id":"2508.07519","title":"Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing","abstract":"Transformer-based diffusion models have recently superseded traditional U-Net architectures, with multimodal diffusion transformers (MM-DiT) emerging as the dominant approach in state-of-the-art models like Stable Diffusion 3 and Flux.1. Previous approaches have relied on unidirectional cross-attention mechanisms, with information flowing from text embeddings to image latents. In contrast, MMDiT introduces a unified attention mechanism that concatenates input projections from both modalities and performs a single full attention operation, allowing bidirectional information flow between text and image branches. This architectural shift presents significant challenges for existing editing techniques. In this paper, we systematically analyze MM-DiT's attention mechanism by decomposing attention matrices into four distinct blocks, revealing their inherent characteristics. Through these analyses, we propose a robust, prompt-based image editing method for MM-DiT that supports global to local edits across various MM-DiT variants, including few-step models. We believe our findings bridge the gap between existing U-Net-based methods and emerging architectures, offering deeper insights into MMDiT's behavioral patterns.","short_abstract":"Transformer-based diffusion models have recently superseded traditional U-Net architectures, with multimodal diffusion transformers (MM-DiT) emerging as the dominant approach in state-of-the-art models like Stable Diffusion 3 and Flux.1. Previous approaches have relied on unidirectional cross-attention mechanisms, with...","url_abs":"https://arxiv.org/abs/2508.07519","url_pdf":"https://arxiv.org/pdf/2508.07519v1","authors":"[\"Joonghyuk Shin\",\"Alchan Hwang\",\"Yujin Kim\",\"Daneul Kim\",\"Jaesik Park\"]","published":"2025-08-11T00:40:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}