Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution

SKILD is a scale‑invariant diffusion model that unifies image generation and continuous super‑resolution within a single unconditional framework. It achieves this by designing a forward process that progressively removes fine‑scale content while adding spectrum‑matched Gaussian noise, treating scale as an explicit diffusion coordinate. The same trained reverse process can generate images or perform super‑resolution simply by changing the starting timestep, yielding strong results on CIFAR‑10, ImageNet, and critical Ising models without task‑specific architecture or retraining.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• diffusion