Verified: a year ago
SafeTensor
Type | |
Stats | 438 1,888 |
Reviews | (81) |
Published | Jan 8, 2024 |
Base Model | |
Training | Steps: 2,000 Epochs: 8 |
Usage Tips | Clip Skip: 1 |
Trigger Words | rattata |
Hash | AutoV2 4A89755957 |
Rattata LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Works very well, has a tendency to go for buck teeth, which may clash with your model's understanding of Rattata. Prompt them out in the negative if you run into this. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on a mixed male/female dataset.