paper-with-me

홈 › Papers

Taming Diffusion Transformer for Real-Time Mobile Video Generation

2025-07-17 · Yushu Wu, Yanyu Li, Anil Kag, Ivan Skorokhodov, Willi Menapace, Ke Ma, Arpit Sahni, Ju Hu, Aliaksandr Siarohin, Dhritiman Sagar, Yanzhi Wang, Sergey Tulyakov

Diffusion Transformers (DiT) have shown strong performance in video generation tasks, but their high computational cost makes them impractical for resource-constrained devices like smartphones, and real-time generation is even more challenging. In this work, we propose a series of novel optimizations to significantly accelerate video generation and enable real-time performance on mobile platforms. First, we employ a highly compressed variational autoencoder (VAE) to reduce the dimensionality of the input data without sacrificing visual quality. Second, we introduce a KD-guided, sensitivity-aware tri-level pruning strategy to shrink the model size to suit mobile platform while preserving critical performance characteristics. Third, we develop an adversarial step distillation technique tailored for DiT, which allows us to reduce the number of inference steps to four. Combined, these optimizations enable our model to achieve over 10 frames per second (FPS) generation on an iPhone 16 Pro Max, demonstrating the feasibility of real-time, high-quality video generation on mobile devices.

📄 PDF Abstract BibTeX arXiv:2507.13343

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Taming Diffusion Probabilistic Models for Character Control

2024-04-23 · Rui Chen, Mingyi Shi, Shaoli Huang, Ping Tan 외

We present a novel character control framework that effectively utilizes motion diffusion probabilistic models to generate high-quality and diverse character animations, responding in real-time to a variety of dynamic us…

Computational EfficiencyDiversity

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

2024-07-17 · Sherwin Bahmani, Ivan Skorokhodov, Aliaksandr Siarohin, Willi Menapace 외

Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is crit…

Video Generation

DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution

2025-03-30 · Zheng-Peng Duan, Jiawei Zhang, Xin Jin, Ziheng Zhang 외

Large-scale pre-trained diffusion models are becoming increasingly popular in solving the Real-World Image Super-Resolution (Real-ISR) problem because of their rich generative priors. The recent development of diffusion …

Image GenerationImage Super-ResolutionSuper-Resolution

E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization

2025-02-13 · Trung X. Pham, Zhang Kang, Ji Woo Hong, Xuran Zheng 외

We propose E-MD3C ($\underline{E}$fficient $\underline{M}$asked $\underline{D}$iffusion Transformer with Disentangled $\underline{C}$onditions and $\underline{C}$ompact $\underline{C}$ollector), a highly efficient framew…

Computational EfficiencyDenoisingGPUSSIM

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

2024-12-12 · CVPR 2025 1 · Dongting Hu, Jierun Chen, Xijie Huang, Huseyin Coskun 외

Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to address all of these challenges by devel…

Knowledge DistillationText-to-Image Generation