# Zoomed In, Diffused Out: Towards Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution

arXiv: https://arxiv.org/abs/2411.12072 · HTML: https://mlsanity.com/paper/2411.12072/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 9 of its 53 references that are in the map.
- First posted on arXiv 18 Nov 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 9 of 9)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)
- [DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2308.15070/) (2023)
- [Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization](https://mlsanity.com/paper/2308.14469/) (2023)
- [XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution](https://mlsanity.com/paper/2403.05049/) (2024)
- [Bigger is not Always Better: Scaling Properties of Latent Diffusion Models](https://mlsanity.com/paper/2404.01367/) (2024)
- [SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time](https://mlsanity.com/paper/2407.15507/) (2024)
- [Dynamic Attention-Guided Diffusion for Image Super-Resolution](https://mlsanity.com/paper/2308.07977/) (2023)
- [Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas](https://mlsanity.com/paper/2408.15660/) (2024)

## Built on by (most cited first, 2 of 2)

- [Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment](https://mlsanity.com/paper/2505.18600/) (2025)
- [BurstGP: Enhancing Raw Burst Image Super Resolution with Generative Priors](https://mlsanity.com/paper/2604.23508/) (2026)

## Abstract (arXiv)

Large-scale, pre-trained Text-to-Image (T2I) diffusion models have gained significant popularity in image generation tasks and have shown unexpected potential in image Super-Resolution (SR). However, most existing T2I diffusion models are trained with a resolution limit of 512x512, making scaling beyond this resolution an unresolved but necessary challenge for image SR. In this work, we introduce a novel approach that, for the first time, enables these models to generate 2K, 4K, and even 8K images without any additional training. Our method leverages MultiDiffusion, which distributes the generation across multiple diffusion paths to ensure global coherence at larger scales, and local degradation-aware prompt extraction, which guides the T2I model to reconstruct fine local structures according to its low-resolution input. These innovations unlock higher resolutions, allowing T2I diffusion models to be applied to image SR tasks without limitation on resolution.