zlacker

>>doener+(OP)
Did anyone test it on 5090? I saw some 30xx reports and it seemed very fast

>>paweld+Uyk
Even on my 4080 it's extremely fast, it takes ~15 seconds per image.

>>Wowfun+eJk
Did you use PyTorch Native or Diffusers Inference? I couldn't get the former working yet so I used Diffusers, but it's terribly slow on my 4080 (4 min/image). Trying again with PyTorch now, seems like Diffusers is expected to be slow.

>>accrua+akl
Uh, not sure? I downloaded the portable build of ComfyUI and ran the CUDA-specific batch file it comes with.

(I'm not used to using Windows and I don't know how to do anything complicated on that OS. Unfortunately, the computer with the big GPU also runs Windows.)

>>Wowfun+Nkl
Haha, I know how it goes. Thanks, I'll give that a try!

Update: works great and much faster via ComfyUI + the provided workflow file.