Sign In

Lunala

84
483
3.4k
30
Verified:
SafeTensor
Type
LoRA
Stats
483
3,418
Reviews
Published
Nov 9, 2023
Base Model
SD 1.5
Training
Steps: 2,000
Epochs: 10
Usage Tips
Clip Skip: 1
Strength: 1
Trigger Words
Lunala
Hash
AutoV2
59599080FA

Lunala LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Very spicy, I recommend adding (dark purple skin, wings) to your prompt to improve consistency. Skin color and patterns are inconsistent. Wing pattern and shape can be unstable. Recommended to lower the LoRA strength if you're running into issues. Despite the problems, good results are possible. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.