The importance of color image quantization is reduce the number of different colors in an image with minimum distortion so, it is one of the most important operations in the computer graphics and image processing.  In this paper, a new algorithm for color image quantization based on a stand-alone harmony search (HS) algorithm is proposed as a first new algorithm. The second algorithm is a hybrid algorithm of K-means and HS. This algorithm is based on a clustering method. Clustering method is one of the most commonly used methods in color image quantization. Investigations results on some of the most commonly used test images in the quantization literature the experiences obtained with these proposed algorithms give high quality images compared with other methods.