DarkViewAI
DarkViewAI
> If `flux_shift ` (with an extra space) is specified, it will be `sigma`. If you train with `sigma`, you should get the same condition. > > If something is...
@kohya-ss thanks
> > and what about the discrete flow shift? when i used the flux shift with the extra space, i used 3.1582? would i still use the same or does...
Does this explain why discreate flow shift was getting passed through the toml? @hinablue because with flow shift , discreate flow shift does not matter
Ahh yes, flux_shift ends up giving you out of vram when you try training the t5, seems to be the issue possibly
yeah it wont work for lora, its only for dreambooth.
would be pretty nice to have lokr support, kohyas implementation is okay, simple tuners seems pretty well done. Need to be able to load in a custom lokr config as...
Caith had made a lokr before, i stuggle with concepts bleeding with regular lora training, https://civitai.com/models/714292/juno-for-flux-by-caith-overwatch-2 I think in general it works better. Here are some keypoints 1. Less prone...
Also im not sure about conv_dim and conv_alpha works good to train those on sdxl , not sure about flux but would be good to have