Welcome to feedback, review & give me more stars and red hearts!
~~
Apr.12
Pleace notice "about this version". 4.0 is Trained with new method.
(*^_^*)/ If u find 4.0 not satisfying enough, just try 1.1.
May.11
Suggested weighted 0.4-0.6.
~~~~~
Famous dubbing actress & Ms. "commissar". (2333)
Type in "younger" to get looking in early 2010s.
~~
Weight around 0.4-0.6. Use it like ordinary LoRA.
~~
Changing training method & editing every txt of tags, this one really takes time. Welcome to give me comment & feedback in favor of me.
~~~~
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
Well, just a appetizer before... Not satisfactory enough.
Luckily meanwhile trained an ordinary lora one.
Here comes the staple food.
Feel easy to start with 768*xxx (like 768*1024) before hires.fix. Weighted around 0.45.
FAQ
Comments (4)
what model you use for the v1.1 preview? looks so good, but I can't replicate it.
You could try Basil related models like chillout or my merge, etc. Pay attention to different preference of each model for negative prompts.
Strongly suggested KanPiroMix now!
That's excellent! thank you!
If possible, Yui Ogura, please 🙇♀️