In order to solve the defects such as ringing effect on boundary of image restoration and weakening of the generality and seriously time consuming of current non-quadratic regularization image restoration algorithm, the anti-distortion and fast image restoration algorithm based on the variable splitting coupled non-circulant blurring model was proposed in this paper. The non-circulant blur model was designed by introducing the mask operator to effectively eleminate the ring effects; and the minimizing cost function was constructed by improving the data fidelity term; then the multiplier alternating direction algorithm was designed by embedding the variable splitting and defining the second auxiliary variable to decouple the circular matrix and the mask matrix of non-circular bluring model to reduce the complexity of this algorithm. Finally, the degraded image was fastly restorated by single-step closed-form updation of the estimation of image based on constrcuting the augmented Lagrange function, and coupling alternating leastmechanism as well as cost function. Simulation results showed that compared with the current image restoration algorithm, the distortion of this algorirhm was smaller; and its convergence speed was faster. This proposed algorithm can fast resrotate multiple types of degraded images, and effectively eleminated the ringing effect of restorated images.