ModelsLab/Harada Takehito (Disgaea Style) (Artist Style) [Illustrious & Noob AI & Pony & SD1.5] - V2

V2 Update (11/19/2023): Trained on a substantially bigger dataset! V1 had 70 images but V2 has 307 images!

Training Data

Trained on: 307 images

Training Model: AnyLoRA_noVae_fp16-pruned

flip_aug: True

Num of Repeats: 5

Unit is Epochs or Steps: Epochs

Number of Epochs or Steps: 10

Training Batch Size: 2

Network Dim: Dim=64; Alpha=32

Lora Creation Process took: 1:16:52