How a Denoising Network Generates Reasonable Looking Images

A denoising neural net seems to be able to start from some configuration of random noise and generate a reasonable looking image. It's really just a matter of human perception to use the images to us, the images generally look right. But what if we want to guide the neural net to generate an image that we'd describe as being of a definite thing like a Picatin-aparti hat? We need to find a way to encode text as an array of numbers. And actually LLM's face the same issue and we can solve it in basically the same way as LLM's do. In the end, what we want to is to derive from any piece of text a feature