yggdrasil75
yggdrasil75
I have over 90 gb of ram. this only started happening within the last week or so. before that, I would not experience any issues switching models unless the model...
now, with flux being massive I fear that larger models will become more common. my 3090 cant handle flux alone, it has to offload into system ram or disk. it...
adding accelerate to inference would be nice, but its also only for linux (accelerate crashes constantly on windows if you can even get it to start at all)
I want to be able to sync my immich data folder to use mega as a backup. should have been added by now.
I had the same issue. it appears to be something wrong with conda, I just decided to not use a virtual environment and it worked fine, detected both gpus.
if you are running them with nvlink, then benefits of multiple drop quickly. with dreamfactory, you would be better off running each standalone. 6 instances of stable diffusion each running...
would be nice. but I dont know how well it would work if the 2 gpus arent linked. though training 2 different models by 2 different gpus would be good....
agreed. though maybe the best option would be that when creating a new chat, ask "do you want to customize the characters" and create a "clone" of the character in...
this mod is quite important for a high quality visual experience. hopefully this is resolved.
can gradio not follow junctions possibly? I do use a junction because I have separate installs that use the same extensions folder.