bycloud
bycloud
@7eu7d7 someone that trained some really good TI actually suggested anythingv3 doesn't do as good as using a mix model between 0.2anime-full&0.8wd, will try both. Just wanna make sure, when...
I had a decent run in replication, however the results doesn't look like the training image of Nahida. This is the .pt that 7eu7d7 provided  This is the...
nice, do u wanna do a PR
it is basically out of memory, try lowering the aabb value instead