Sign In

Mudkip

59

304

43

20

Verified:

SafeTensor

Type

LoRA

Stats

304

43

1

Reviews

Published

Jan 17, 2024

Base Model

SD 1.5

Training

Steps: 1,800
Epochs: 8

Usage Tips

Clip Skip: 1

Trigger Words

mudkip

Hash

AutoV2
9C6658DCC1

Mudkip LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Works great, the main issue is tail placement and color. It can show up in weird places and will sometimes be blue. Otherwise quite consistent. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on a mixed male/female dataset.