(Welcome to feedback, review & give me more stars and red hearts)
~~
Apr.12
Pleace notice "about this version". 2.0 is Trained with new method. Suggested weighted 0.6.
~~~~~
(Surprising failure on using Delibrate v11 or AresMix after switching to another GTX3080 online.) Then I discovered that training on default model.ckpt (seems NAI) can give good results as well.
Suggested weight around 0.8 on Basil related models.
~~
Hires.fix on is suggested as always (e.g. 448*640--1.6x-->716*1024, Hires steps 18,Denoising strength 0.45, latent.)
~~
Be kind to these lovely.
Legal & Risk
It is prohibited to use this model for commercial purposes and any scenarios of illegal acts and purposes.
Description
(Trained on default)
FAQ
Comments (1)
This type of shit makes me sad that I can't run LORAs on my system. The example images look great, hope to review it one day :D