now see, this is with sora. it knows who misty is, it does actually know what a dodge magnum is, but it doesn't know who casey or nanako is. this is why we have to do this in many stages, producing various images of steadily increasing quality until we are happy with the result. this is not a one and done thing, especially for such a complicated image: we have two different characters doing something dynamically, most of their bodies are obscured, and we have a kind of unpopular, but fortunately very distinctive looking car.
do not heckle the slopsmith.