New lora for shizuku from DOAXVV.Trigger word is shizuku.All images she had her ears were also tagged "fox ears" but they will show up most of the without it. You can put "fox ears" in the negative to try not having them.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.I trained this model on perfectworld but it should work reasonably well in a variety of similar models.Two versions:Normal version I just trained like normal. However since 90% of the images I could get are just on her default swimsuit, the model will try to put her in that suit if it can.Second version I trained with a mix of screenshots and images generated from the first lora and perfect world. This one is more versatile in terms of her clothing but has a more 2.5D feel. Also her hair color is more easily lost with this one.Will retrain in a while when I can find better pics of shizuku online that have her in various clothes. I don't have doaxvv account but if you do and can take some screenshots, I'd be grateful!

DOAXVV - Shizuku

doa_shizuku.safetensors

v1.0 (base)

v1.0 (versatile)

More versatile clothing but looks a little flatter and 2.5d

Files with SHA256: c16097cbacbd2b0e433904a99a082f01ce2f20af09b4db3341f69856880db23f