This is incorrect. Generative image models don’t contain databases of artwork. If they did, they would be the most amazing fucking compression technology, ever.
… snip…
The training is mostly a linear process. So the images never really get loaded into an database, they just get read along with their metadata into a GPU where it performs some Machine Learning stuff to generate some arrays of floating point values. Those values ultimately will end up in the model file.
Where does it get read from? a database, right? yeah. that’s called a database. It may not be a large massive repository of art to rival the Vatican’s secret collection, but it is a database of digital art.
as for it being complex… yeah. that’s why I kept it simple and glossed over all the complex stuff that’s not really, you know. relevant to the question of who owns it.
No, a .safetensors file is not a database. You can’t query a .safetensors file and there’s nothing like ACID compliance (it’s read-only).
Imagine a JSON file that has only keys and values in it where both the keys and the values are floating point numbers. It’s basically gibberish until you go through an inference process and start feeding random numbers through it (over and over again, whittling it all down until you get a result that matches the prompt to a specified degree).
How do the “turbo” models work to get a great result after one step? I have no idea. That’s like black magic to me haha.
Where does it get read from? a database, right? yeah. that’s called a database. It may not be a large massive repository of art to rival the Vatican’s secret collection, but it is a database of digital art.
as for it being complex… yeah. that’s why I kept it simple and glossed over all the complex stuff that’s not really, you know. relevant to the question of who owns it.
No, a .safetensors file is not a database. You can’t query a .safetensors file and there’s nothing like ACID compliance (it’s read-only).
Imagine a JSON file that has only keys and values in it where both the keys and the values are floating point numbers. It’s basically gibberish until you go through an inference process and start feeding random numbers through it (over and over again, whittling it all down until you get a result that matches the prompt to a specified degree).
How do the “turbo” models work to get a great result after one step? I have no idea. That’s like black magic to me haha.