I'm still learning.... At least the LoRA is rather small this time
Trained on AnimagineXL v3.1
Trigger word: snmr (or 1girl, shiina mahiru \(otonari no tenshi-sama\), otonari no tenshi-sama)
Recommended strength: 1.0
Dataset: 459 images (included mirrored, region cropped images, removed low quality image, captioned using WD1.4 tagger)
Train through 20 epochs, 4 images per batch