Wide-angle cameras, despite their popularity for con- tent creation, suffer from distortion-induced facial stretch- ing—especially at the edge of the lens—which degrades vi- sual appeal. To address this issue, we propose a structure- to-detail portrait correction model named ImagePC. It in- tegrates the long-range awareness of transformer and multi- step denoising of diffusion models into a unified framework, achieving global structural robustness and local detail refine- ment. Besides, considering the high cost of obtaining video labels, we then repurpose ImagePC for unlabeled wide-angle videos (termed VideoPC), by spatiotemporal diffusion adap- tion with spatial consistency and temporal smoothness con- straints. For the former, we encourage the denoised image to approximate pseudo labels following the wide-angle distor- tion distribution pattern, while for the latter, we derive rectifi- cation trajectories with backward optical flows and smooth them. Compared with ImagePC, VideoPC maintains high- quality facial corrections in space and mitigates the potential temporal shakes sequentially in blind scenarios. Finally, to establish an evaluation benchmark and train the framework, we establish a video portrait dataset with a large diversity in people number, lighting conditions, and background. Experi- ments demonstrate that the proposed methods outperform ex- isting solutions quantitatively and qualitatively, contributing to high-fidelity wide-angle videos with stable and natural por- traits. The codes and dataset will be available.