Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-05-25 with 11 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Zixin Jessie Chen et al. |
| Year | 2026 |
| HF Upvotes | 11 |
| arXiv | 2605.26032 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce SKILD, a Scale-invariant K-Space Image Learning Diffusion model that unifies generation and continuous super-resolution within a single unconditional framework. Both natural images and critical physical systems exhibit scale invariance, and we leverage it to design a forward process that attenuates image content from fine to coarse scales while injecting spectrum-matched Gaussian noise, making scale an explicit coordinate of the diffusion dynamics. The same trained reverse process performs generation and continuous super-resolution by varying only the starting timestep: no task-specific architecture, no conditioning branch, no classifier-free guidance, no retraining per scale factor. Empirically, SKILD reaches FID 2.65 and Inception Score 9.63 on unconditional CIFAR-10, performs 2times--8times super-resolution on ImageNet from a single unconditional checkpoint while outperforming conditional models across perceptual metrics, and reconstructs critical Ising models whose connected four-point correlations closely track the ground truth.
Engineering Breakdown
The Problem
Despite their practical differences, both can be understood as reversing information loss across scales.
The Approach
We introduce SKILD, a Scale-invariant K-Space Image Learning Diffusion model that unifies generation and continuous super-resolution within a single unconditional framework.
Key Results
Empirically, SKILD reaches FID 2.65 and Inception Score 9.63 on unconditional CIFAR-10, performs 2times--8times super-resolution on ImageNet from a single unconditional checkpoint while outperforming conditional models across perceptual metrics, and reconstructs critical Ising models whose connected four-point correlations closely track the ground truth.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Everything
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::