V2
V2 Update (11/02/2023): V2 is trained with a new dataset that and is trained on the Anime checkpoint instead of AnyLora. It has better hands, better clothes accuracy, and is more flexible (I absorbed less tags into the trigger).
Training Data
Trained on: 33 images
Training Model: Animefull-final-pruned-fp16
flip_aug: True
Num of Repeats: 10
Unit is Epochs or Steps: Epochs
Number of Epochs or Steps: 10
Training Batch Size: 2
Network Dim: 16
V1
Weight: 0.8
Trigger: Lana_Pokemon
<-- Same as the Lora file name, isn't that easy to remember?
Extra prompts: sailor collar, sleeveless shirt, blue pants,
Trained on 94
images