We introduce DiffFNO, a novel framework for arbitrary-scale super-resolution that incorporates a Weighted Fourier Neural Operator (WFNO) enhanced by a diffusion process. DiffFNO's adaptive mode weighting mechanism in the Fourier domain effectively captures critical frequency components, significantly improving the reconstruction of high-frequency image details that are essential for super-resolution tasks.Additionally, we propose a Gated Fusion Mechanism to efficiently integrate features from the WFNO and an attention-based neural operator, enhancing the network's capability to capture both global and local image details. To further improve efficiency, DiffFNO employs a deterministic ODE sampling strategy called the Adaptive Time-step ODE Solver (AT-ODE), which accelerates inference by dynamically adjusting step sizes while preserving output quality.Extensive experiments demonstrate that DiffFNO achieves state-of-the-art results, outperforming existing methods across various scaling factors, including those beyond the training distribution, by a margin of 2–4 dB in PSNR. Our approach sets a new standard in super-resolution, delivering both superior accuracy and computational efficiency.