paper-with-me

홈 › Papers

DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation

2025-03-13 · Chen Chen, Rui Qian, Wenze Hu, Tsu-Jui Fu, Lezhi Li, BoWen Zhang, Alex Schwing, Wei Liu, Yinfei Yang

In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based architectures--including PixArt-style and MMDiT variants--and compare them with a standard DiT variant which directly processes concatenated text and noise inputs. Surprisingly, our findings reveal that the performance of standard DiT is comparable with those specialized models, while demonstrating superior parameter-efficiency, especially when scaled up. Leveraging the layer-wise parameter sharing strategy, we achieve a further reduction of 66% in model size compared to an MMDiT architecture, with minimal performance impact. Building on an in-depth analysis of critical components such as text encoders and Variational Auto-Encoders (VAEs), we introduce DiT-Air and DiT-Air-Lite. With supervised and reward fine-tuning, DiT-Air achieves state-of-the-art performance on GenEval and T2I CompBench, while DiT-Air-Lite remains highly competitive, surpassing most existing models despite its compact size.

📄 PDF Abstract BibTeX arXiv:2503.10618

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation

2026-05-24 · Zichao Yue, Zhiru Zhang arxiv

Pre-propagation graph neural networks (PPGNNs) decouple node feature propagation from transformation: graph diffusion is performed once as preprocessing, and training reduces to dense per-node transformations. This desig…

MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices

2023-11-28 · Yang Zhao, Yanwu Xu, Zhisheng Xiao, HaoLin Jia 외

The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed. In this paper, we propose \textbf{MobileDiffusion}, a highly efficient t…

Computational EfficiencyImage GenerationText to Image GenerationText-to-Image Generation

Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis

2024-06-08 · CVPR 2024 1 · Zanlin Ni, Yulin Wang, Renping Zhou, Jiayi Guo 외

The field of image synthesis is currently flourishing due to the advancements in diffusion models. While diffusion models have been successful, their computational intensity has prompted the pursuit of more efficient alt…

Image Generation

LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures

2025-11-13 · Wenzhe He, Xiaojun Chen, Ruiqi Wang, Ruihui Li 외 arxiv

3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models for high-fidelity reconstruction. However…

Point Cloud CompletionLidar Scene CompletionAutonomous VehiclesPoint Clouds

Principled Approximation Methods for Efficient and Scalable Deep Learning

2025-08-29 · Pedro Savarese arxiv

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider …

Neural Architecture SearchImage ClassificationModel Compression