ExtraVAR enables resolution extrapolation in visual autoregressive models by stage-aware RoPE remapping and entropy-driven attention scaling, suppressing repetition and detail loss.
I-max: Maximize the resolu- tion potential of pre-trained rectified flow transformers with projected flow
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
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.
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 3years
2026 3roles
baseline 1polarities
baseline 1representative citing papers
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
UltraDiffEdit enables tuning-free image editing at up to 8K resolution on a single consumer GPU by combining multi-patch latent encoding, boundary-aware denoising, and hybrid local-global-upsample sampling.
citing papers explorer
-
ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
ExtraVAR enables resolution extrapolation in visual autoregressive models by stage-aware RoPE remapping and entropy-driven attention scaling, suppressing repetition and detail loss.
-
HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
-
Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing
UltraDiffEdit enables tuning-free image editing at up to 8K resolution on a single consumer GPU by combining multi-patch latent encoding, boundary-aware denoising, and hybrid local-global-upsample sampling.