Early detection of skin and oral cancers is essential for improving survival rates and reducing treatment costs, yet conventional diagnostic methods remain resource-intensive and limited in accessibility. This study presents a transformer-based deep learning framework for automated skin and oral cancer detection using models including Multi-ViT, MA-Transformer V2, MobileUNETR, TinyViT, and Xception. Evaluated on the PAD-UFES-20 and Oral Cancer datasets, the proposed multi-ViT achieved high performance, with 99.12% accuracy on the PAD-UFES-20 dataset and 99.37% on the Oral Cancer dataset, while maintaining high F1-scores and AUC-PR values across both datasets. A unified pipeline incorporating targeted preprocessing, model training, and lightweight deployment was developed, enabling real-time screening through a web-based application. This allows users to upload lesion images and receive instant predictions, supporting early intervention without requiring specialized equipment. The proposed system contributes to practical, scalable cancer screening, aiding timely diagnosis and improving healthcare accessibility in diverse clinical and community settings.