Portal buyers would be suspicious
Portal buyers would be suspicious
You can run a 7b model on cpu really fast even on a phone.
doesnt work anyway lol
you need to learn the difference between opinion and fact then
Still its neither implemented in a1111,fooocus and comfyui. I acknowledge, it exists and certainly works, but was not adapted by any tool i know of
thats almost a year old. and their github 2 years. also i did train multiple loras with only ai generated images with sd1.5 and XL without any issue
Screenshot and its gone
Thats not how it works at all
Not really. Check midjourney v6 generated images. I found many images, which look undistinctable from real images. So i dont see, why image generation should get worse. What matters is the dataset and only dataset. It doesnt matter if the model is trained on ai images, as long as the dataset is good
Sooo how long until theres a plugin in a1111?
sure, but its still written on paper. fire still does its thing
my gf loves it when i make noise
if you have enough money, pay for stuff you like.
its already possible, but not really good atm. saw some scenes, where they changed the aspect ratio from 16:9 to tiktok. im waiting for realfill, which google is working on. idk how it works, but it can guess, what should be outside of the image and the images i saw were pretty amazing compared to SD. 4k upscaling at 120hz also no problem, as i did this to the first season of spongebob and it really works fine with my hobby equipment in one night. id really love to see an upscaled 16:9 version of the it crowd and the first 6 seasons of scrubs.
edit: this is what i was referring to https://youtu.be/bD_HyxHMHPo?si=-ktJz3GuBNHhn9UY
nearby share
at least i do have 2 servers. one main and one backup
Even if it will plateau, same was said with moorrs law, which held up way longer than expected. There are so many ways to improve this. Open source community is getting to the point where you can actually run decent models on normal private hardware (talking about 70-120b model)