Sign In

Minccino

75
452
2.8k
29
Verified:
SafeTensor
Type
LoRA
Stats
452
2,847
Reviews
Published
Nov 6, 2023
Base Model
SD 1.5
Training
Steps: 2,000
Epochs: 8
Usage Tips
Clip Skip: 1
Strength: 1
Trigger Words
Minccino
Hash
AutoV2
9B4448B383

Minccino LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Incredibly consistent, only issue is the tail being absent in some images which is easily fixed by prompting for it. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on a mixed male/female dataset.