Verified: a year ago
SafeTensor
Type | |
Stats | 893 8,159 |
Reviews | (137) |
Published | Nov 5, 2023 |
Base Model | |
Training | Steps: 2,400 Epochs: 8 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Trigger Words | Riolu |
Hash | AutoV2 C4244691BA |
Riolu LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Very consistent except for bras and bikinis, for whatever reason her fur color goes wonky when those come into the mix. Works very consistently otherwise. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.