andy8992
andy8992
It feels like flux is and the features added to optimize it are slowly making all other models in forge slower. Constantly reloading every model each time no matter what,...
> > I guess this is what destroyed performance for me, +20-30 sec per generation after update. I don't even care about flux. > > Why? it's not been finetuned...
I realized what is happening here. Logically, you would expect that each time you hit the highresfix button, the scale factor would continue to multiply based on the newly upscaled...
> I just used ComfyUI, it seems that models are now kept in VRAM and generation with same prompt takes 30s for me while changing the prompt takes 47.47s (AR:...
Ah I just meant I was getting constant model movement even in xl
> It's just swapping it from VRAM to SYSRAM, which is negligible in speed difference, while integral to keeping from having bugs and also for general memory management to keep...
> It takes much longer if you're just on the edge of using all your system ram. For me it adds almost 1 minute. If parts of the model were...
> I set it to Swap Method:Async,Swap Location:Shared,now I don't have to reload the model every time! nice, i have to blindly tweak a lot of things to reduce this,...
Been the case since it was implemented for me, tbh I didn't quite understand what its for anyway.