Single Image Super-Resolution (SISR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. Deep learning, especially Convolutional Neural Networks (CNNs), has advanced SISR. However, increasing network depth increases parameters, and memory usage, and slows training, which is problematic for resource-limited devices. To address this, lightweight models are developed to balance accuracy and efficiency. We propose the Involution & BSConv Multi-Depth Distillation Network (IBMDN), combining Involution & BSConv Multi-Depth Distillation Block (IBMDB) and the Contrast and High-Frequency Attention Block (CHFAB). IBMDB integrates Involution and BSConv to balance computational efficiency and feature extraction. CHFAB enhances high-frequency details for better visual quality. IBMDB is compatible with other SISR architectures and reduces complexity, improving evaluation metrics like PSNR and SSIM. In transformer-based models, IBMDB reduces memory usage while improving feature extraction. In GANs, it enhances perceptual quality, balancing pixel-level accuracy with perceptual details. Our experiments show that the method achieves high accuracy with minimal computational cost. The code is available at GitHub.