bycloud

Results 14 comments of 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 ![xy_grid-0064-30-7-None-Euler a-1662428442-6569e224-20221117183202](https://user-images.githubusercontent.com/29135514/202583097-3003ca5f-7025-409f-ad52-848c0b5ac949.png) This is the...

it is basically out of memory, try lowering the aabb value instead