"soup" == soup <soupforare@gmail.com> writes:
They began leveraging large language models against... any data set as I understand it. There were a few papers that set the world on fire with their implementations. Academia was raided for questionably sourced corpus for commercial use veiled in community gain.
I've been wrenching on stable diffusion API for a few weeks, as a former professional photographer it is shocking to me the quality you can get from very little input and common COTS GPUs. Haven't touched any of the SaaS cloud inferencing services that have come out in this gold rush but they can do quite a lot more with the datacenter class GPU grunt. Text to video (so-called "T2V") is here and getting scary.~
You have to have a recent nVidia CPU to get good results, I was trying using AMD GPUs and it just wasn't fast at all. So instead of spending $500 on a GPU, I think spending $20 on some cloud rental might be a good use of my money and time. Still watiing on <blanking on his name> to post his setup instructions from New Orleans so we can all start poking at it. Now one big issue I see is that once get generate an image, can you get a version broken into layers? Do professional artists work mostly in layers on computers so they can more easily re-compose their layout? For some of the examples, I though it was really neat, but I'd like to shift the result to the left say to emphasize the background more. But since I'm a terrible artist without any training or much talent, I leave it to others to answer these questions.