This paper presents a novel approach to real-time arbitrary style transfer using adaptive instance normalization (AdaIN). The method addresses the limitations of existing techniques, which either require slow iterative optimization or are restricted to a fixed set of styles. AdaIN aligns the mean and variance of content features with those of style features, enabling flexible and fast style transfer. The approach is based on a feed-forward neural network, achieving speeds comparable to the fastest existing methods while maintaining the flexibility to transfer to arbitrary styles. The paper also introduces user controls such as content-style trade-off, style interpolation, and spatial and color controls, all implemented using a single feed-forward network. Experimental results demonstrate the effectiveness and efficiency of the proposed method, showing superior performance in terms of speed and flexibility compared to previous methods.This paper presents a novel approach to real-time arbitrary style transfer using adaptive instance normalization (AdaIN). The method addresses the limitations of existing techniques, which either require slow iterative optimization or are restricted to a fixed set of styles. AdaIN aligns the mean and variance of content features with those of style features, enabling flexible and fast style transfer. The approach is based on a feed-forward neural network, achieving speeds comparable to the fastest existing methods while maintaining the flexibility to transfer to arbitrary styles. The paper also introduces user controls such as content-style trade-off, style interpolation, and spatial and color controls, all implemented using a single feed-forward network. Experimental results demonstrate the effectiveness and efficiency of the proposed method, showing superior performance in terms of speed and flexibility compared to previous methods.