paper-with-me

홈 › Papers

ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices

2026-05-15 · Kunpeng Du, Haizhen Xie, Sen Lu, Lei Yu, Binglei Bao, Huaao Tang, Chuntao Liu, Hao Wu, Yang Zhao, Zhicai Huang, Heyuan Gao, Zhijun Tu, Jie Hu, Xinghao Chen arxiv

The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices entails prohibitive computational and memory overhead. While efficiency-driven approaches like Linear-DiT and static pruning alleviate bottlenecks, they often incur quality degradation. Unlike cloud environments, mobile constraints require a single-model paradigm that dynamically balances fidelity and latency. We introduce ElasticDiT, which achieves this dynamic trade-off by adjusting spatial compression ratios and DiT block depths. By integrating Shift Sparse Block Attention (SSBA) and a Tiny DWT-Distilled VAE (T-DVAE), ElasticDiT reduces inference latency and memory footprint while maintaining image quality. Experiments confirm that ElasticDiT effectively covers a wide range of fidelity-latency trade-offs within a single set of parameters. By jointly adjusting compression and depth, a single ElasticDiT model can be reconfigured on-the-fly to outperform task-specific baselines. Specifically, our flex lite variant achieves an HPS of 32.87, surpassing the Flux model, while maintaining competitive quality at 84.16 percent average sparsity through SSBA. Furthermore, the plug-and-play T-DVAE provides SD3-level reconstruction with only 1/8x the computational cost of standard VAEs, and Flow-GRPO boosts semantic alignment (GenEval: 66.93 to 73.62). These results demonstrate that ElasticDiT offers a versatile, hardware-adaptive solution that eliminates the need for multiple specialized models, providing a promising path for future high-resolution image generation on mobile devices.

📄 PDF Abstract BibTeX arXiv:2605.15684

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

2026-01-13 · Dongting Hu, Aarush Gupta, Magzhan Gabidolla, Arpit Sahni 외 arxiv

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an e…

Image Generation

Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers

2023-09-23 · Adam Pardyl, Grzegorz Kurzejamski, Jan Olszewski, Tomasz Trzciński 외

Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches. It limits their applicability in real-world problems, such as active visual e…

Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

2025-09-23 · Shufan Li, Jiuxiang Gu, Kangning Liu, Zhe Lin 외 arxiv

We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support simple image-level understanding tasks …

Text-to-Image GenerationMultimodal ReasoningImage Editing

One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers

2026-03-12 · Moayed Haji-Ali, Willi Menapace, Ivan Skorokhodov, Dogyun Park 외 arxiv

Diffusion transformers (DiTs) achieve high generative quality but lock FLOPs to image resolution, limiting principled latency-quality trade-offs, and allocate computation uniformly across input spatial tokens, wasting re…

ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions

2024-07-11 · Jiu Feng, Mehmet Hamza Erol, Joon Son Chung, Arda Senocak

Transformers have rapidly overtaken CNN-based architectures as the new standard in audio classification. Transformer-based models, such as the Audio Spectrogram Transformers (AST), also inherit the fixed-size input parad…

AllAudio Classification