Ryuichi @ryuichi@qoto.org
Discover a new world of digital imagery produced through the advanced machine learning algorithms we utilize. Follow our account to witness stunning visuals generated through the latest in technology and computer science.
Joined Apr 2023
Ryuichi
boosted
Ryuichi
boosted
Lora, called flat and flat2, intentionally learns low-detail images, which apparently improves the detail of generated images when Lora strength is specified with a negative value. For example, it can be specified as <lora:flat2:-1>. It's a interesting idea.
@moosed and we're near mother's day over here so it's apt in celebration!
Ryuichi
boosted
@Elfie almost there wut
Ryuichi
boosted
@nop check the other replies from
dtzbts~maid in my original post, he explains a bit more stuff and uploads some screenshots.
Ryuichi
boosted
@ryuichi@qoto.org https://comfyanonymous.github.io/ComfyUI_examples/faq/ explains it better then i can.
The main benefit for me is control over upscale, instead of doing one big hiresfix step, I have a custom workflow that's a couple of small upscales instead of one big. The prompting is mostly the same, I never really used weights that much so the different behaviour isn't really an issue. Heres an example of my workflow, its somewhat overloaded, but i have plenty of flexibility with just moving couple of outputs around.
@maid i see, so it's like a totally new way to generate images you have to get used to
Well i can see the advantages of the system, probably wouldn't be bad to give it a try.
Discover a new world of digital imagery produced through the advanced machine learning algorithms we utilize. Follow our account to witness stunning visuals generated through the latest in technology and computer science.
Joined Apr 2023
