# SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers

arXiv: https://arxiv.org/abs/2605.22668 · HTML: https://mlsanity.com/paper/2605.22668/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 43 of its 48 references that are in the map.
- First posted on arXiv 21 May 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens](https://mlsanity.com/paper/2402.13753/) (2024)
- [Rotary Position Embedding for Vision Transformer](https://mlsanity.com/paper/2403.13298/) (2024)
- [ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models](https://mlsanity.com/paper/2310.07702/) (2023)
- [DemoFusion: Democratising High-Resolution Image Generation With No ](https://mlsanity.com/paper/2311.16973/) (2023)
- [FiT: Flexible Vision Transformer for Diffusion Model](https://mlsanity.com/paper/2402.12376/) (2024)
- [Matryoshka Diffusion Models](https://mlsanity.com/paper/2310.15111/) (2023)
- [RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers](https://mlsanity.com/paper/2502.15894/) (2025)
- [Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2503.18352/) (2025)
- [FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.12963/) (2024)
- [Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis](https://mlsanity.com/paper/2306.08645/) (2023)
- [Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation](https://mlsanity.com/paper/2402.10491/) (2024)
- [DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance](https://mlsanity.com/paper/2406.18459/) (2024)
- [AccDiffusion: An Accurate Method for Higher-Resolution Image Generation](https://mlsanity.com/paper/2407.10738/) (2024)
- [FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion](https://mlsanity.com/paper/2412.09626/) (2024)

## Built on by (most cited first, 3 of 3)

- [JoLT: Joint Latent Trajectories for Context-Guided High-Resolution Tiled Generation](https://mlsanity.com/paper/2608.15395/) (2026)
- [PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising](https://mlsanity.com/paper/2606.30968/) (2026)
- [AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers](https://mlsanity.com/paper/2610.17227/) (2026)

## Abstract (arXiv)

Diffusion transformers (DiTs) have emerged as a dominant architecture for text-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 through Rotary Position Embeddings (RoPE) extrapolation combined with attention 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's spatial-frequency structure at each denoising step. This adaptive scaling improves both structural coherence and fine-detail fidelity. Experiments show that SEGA consistently improves high-resolution synthesis across multiple target resolutions, outperforming state-of-the-art training-free baselines.