Lora for nanami. Trigger word is nanami.
I recommend ADetailer or hi res fix if your faces are coming out bad at low res. Most of my sample images are using ADetailer.
v2
Different training set, different training parameters. A little different stylistically but should look more like her. Trained against perfect world.
v1
Original. Trained against fantexi v0.8
Description
FAQ
Comments (6)
No matter how many times I make LoRA, I can't make it look like the original like you.
What kind of training do you do when creating LoRA?
If you use a1111 you can click the little (i) button on the lora card to see the training settings of mine. If you have more questions i can try answer but loras can be a little fickle.
@stubatme Sorry for the late thank you.
@stubatme I have one question.What did you do to improve the quality from V1 to V2?
@yu_tubameyahooco6071 i think the v1s were a little undertrained. Tweaked a bunch of settings but i think switching to prodigy/dadapt was a big part of it
@stubatme Thank you for answering.I 'll try it.
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.