Comment on How does generative AI create convincing lighting in images?

mkwt@lemmy.world ⁨4⁩ ⁨months⁩ ago

The deal with LLMs is that it’s very difficult to say which piece of training material went into which output. Everything gets chopped up and mixed, and it’s computationally difficult to run backwards.

My understanding of the image generators is that they operate one pixel at a time too, looking only at neighboring pixels. So in that sense, it’s not correct to say they understand the context of anything.

source
Sort:hotnewtop