paper-with-me

Papers

I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow

2024-10-10 · Ruoyi Du, Dongyang Liu, Le Zhuo, Qin Qi, Hongsheng Li, Zhanyu Ma, Peng Gao

Rectified Flow Transformers (RFTs) offer superior training and inference efficiency, making them likely the most viable direction for scaling up diffusion models. However, progress in generation resolution has been relatively slow due to data quality and training costs. Tuning-free resolution extrapolation presents an alternative, but current methods often reduce generative stability, limiting practical application. In this paper, we review existing resolution extrapolation methods and introduce the I-Max framework to maximize the resolution potential of Text-to-Image RFTs. I-Max features: (i) a novel Projected Flow strategy for stable extrapolation and (ii) an advanced inference toolkit for generalizing model knowledge to higher resolutions. Experiments with Lumina-Next-2K and Flux.1-dev demonstrate I-Max's ability to enhance stability in resolution extrapolation and show that it can bring image detail emergence and artifact correction, confirming the practical value of tuning-free resolution extrapolation.

📄 PDF Abstract BibTeX arXiv:2410.07536

Code (0)

등록된 구현이 없습니다.

Tasks

2k

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

NAMI: Efficient Image Generation via Progressive Rectified Flow Transformers

2025-03-12 · Yuhang Ma, Bo Cheng, Shanyuan Liu, Ao Ma 외

Flow-based transformer models for image generation have achieved state-of-the-art performance with larger model parameters, but their inference deployment cost remains high. To enhance inference performance while maintai…

Image Generation

GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow

2025-10-31 · Mengbo Wang, Shourya Verma, Aditya Malusare, Luopin Wang 외 arxiv

Spatial transcriptomics (ST) technologies can be used to align transcriptomes with histopathological morphology, presenting exciting new opportunities for biomolecular discovery. Using ST data, we construct a novel frame…

Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling

2025-08-10 · Hongyang Zhou, Xiaobin Zhu, Liuling Chen, Junyi He 외 arxiv

Unsupervised real-world super-resolution (SR) faces critical challenges due to the complex, unknown degradation distributions in practical scenarios. Existing methods struggle to generalize from synthetic low-resolution …

Few-step Generative Models as Lossy Compression

2026-06-09 · Fuma Kimishima, Jinjia Zhou arxiv

DiffC provides a principled way to reuse pre-trained diffusion models for lossy compression, but its encoding and decoding procedures remain slow because they require many discretized forward and reverse steps. We study …

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

2024-05-13 · Hanshu Yan, Xingchao Liu, Jiachun Pan, Jun Hao Liew 외

We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in…