Retrive image from from features represented by histograms of oriented gradients

I am using histogram of oriented gradients for image classification using clustering in scikit learn. I am using hog from scikit-image to generate hog from 512x512 grayscale image. Here is an example:

fd, hog_image = hog(image, orientations=8, pixels_per_cell=(16, 16),
                    cells_per_block=(1, 1), visualize=True, channel_axis=-1)

Where fd is used as features in classification. I wonder if there is a way to retrieve image from fitted coefficients in clustering model, in order to see how features differ between the clusters.(i.e go from fd to 512x512 image visualizing hog)