skylerblack2

I get the same result as OP whenever I use the default upscaler titled 'Latent'. The problem goes away when I switch to another upscaler like ESRGAN_4X. I'm not aware...

> ### Discussed in #2103 > Originally posted by **GodFazer** January 30, 2024 I had tried to use many of SDXL models but often they don`t give result as some...

> > 1. faceswap should be the last stage and not the first, otherwise the connected loras will distort the portrait resemblance. Actually this is a bug! > > 2....

same issue on MacOs. Has anyone found a way to shave off those 30 seconds form every generation?

i have the same issue. it works on txt2img but not img2img. in txt2img i also see a warning in the console logs that looks like this: ...\AppData\Roaming\Python\Python310\site-packages\insightface\utils\transform.py:68: FutureWarning: `rcond`...

this is the cookbook i'm talking about that i'd like to see improved. 1/ if there's anywhere in that guide that includes a code snippet i can copy paste, swap...