I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow
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.
Code (0)
등록된 구현이 없습니다.
Tasks
2kMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
NAMI: Efficient Image Generation via Progressive Rectified Flow Transformers
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 GenerationGeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow
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
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
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
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…