SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
Summary
SEGA is a training-free method that improves high-resolution text-to-image generation by adaptively scaling attention across RoPE components based on spatial-frequency structure during denoising steps.
View Cached Full Text
Cached at: 05/22/26, 02:20 PM
Paper page - SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
Source: https://huggingface.co/papers/2605.22668
Abstract
SEGA improves high-resolution text-to-image generation by adaptively scaling attention across RoPE components based on spatial-frequency structure during denoising steps.
Diffusion transformers(DiTs) have emerged as a dominant architecture fortext-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by modifying inference-time attention behavior, often throughRotary Position Embeddings(RoPE) extrapolation combined withattention scaling. However, these strategies apply a uniform and content-agnostic scaling across RoPE components with distinct frequency characteristics, inducing a trade-off between preserving global structure and recovering fine detail. We introduce SEGA, a training-free method that dynamically scales attention across RoPE components according to the latent’sspatial-frequency structureat each denoising step. This adaptive scaling improves both structural coherence and fine-detail fidelity. Experiments show that SEGA consistently improveshigh-resolution synthesisacross multiple target resolutions, outperforming state-of-the-art training-free baselines.
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2605\.22668
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.22668 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.22668 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.22668 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion
CogSENet introduces a blind image deblurring framework inspired by eagle vision, using semantic-aware modules and frequency decomposition to improve restoration quality and structural fidelity, outperforming state-of-the-art methods.
RefGC-SR^2: Reference-guided Generated Content Super-Resolution and Refinement
This paper introduces a new task, reference-guided generated content super-resolution-refinement (RefGC-SR²), which simultaneously recovers high-resolution details and refines generative artifacts using a frequency-aware diffusion transformer model. The method leverages a high-resolution reference image to improve the quality of AI-generated images during post-processing.
Spectral Guidance for Flexible and Efficient Control of Diffusion Models
Introduces Spectral Guidance, a framework for controlling diffusion models by leveraging low-dimensional representations of the diffusion process, enabling flexible and stable control without task-specific retraining or backpropagation through the denoiser.
Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
This paper proposes Nemotron-Labs-Diffusion-Image, a masked discrete diffusion model for high-resolution text-to-image synthesis, introducing a token-editing mechanism and grouped cross-entropy objective to improve token refinement and training efficiency.
Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation
This paper introduces SemanticSeg, a large-scale dataset for semantic segmentation of long texts, and block distillation, a training framework that enables block attention models to approach full-attention performance, improving KV cache reuse in RAG and long-context scenarios.