Automatic image annotation is an important task for multimedia retrieval. By allocating relevant words to un-annotated images, these images can be retrieved in response to textual queries. There are many researches on the problem of image annotation and most of them construct models based on joint probability or posterior probabilities of words. In this paper we estimate the probabilities that words generate the images, and propose a two-phase generation model for the generation procedure. Each word first generates its related words, then these words generate an un-annotated image, and the relation between the words and the un-annotated image is obtained by the probability of the two-phase generation. The textual words usually contain more semantic information than visual content of images, thus the probabilities that words generate images is more reliable than the probability that images generate words. As a result, our model estimates the more reliable probability than other probabilistic methods for image annotation. The other advantage of our model is the relation of words is taken into consideration. The experimental results on Corel 5K and MIR Flickr demonstrate that our model performs better than other previous methods. And two-phase generation which considering word's relation for annotation is better than one-phase generation which only consider the relation between words and images. Moreover, the methods which estimate the generative probability obtain better performance than SVM which estimates the posterior probability.