Verified: a year ago
SafeTensor
Type | |
Stats | 752 5,562 |
Reviews | (124) |
Published | Oct 12, 2023 |
Base Model | |
Training | Steps: 2,000 Epochs: 8 |
Usage Tips | Clip Skip: 1 |
Trigger Words | Zeraora |
Hash | AutoV2 A80BD7C0EF |
Zeraora LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. 'Tail' placement is very unstable, especially if you're using a furry base model, it'll try and put the tail in the 'normal' place instead of between her shoulder blades like it's technically supposed to. Fur patterns can be inconsistent. Legs should be black from the knee down, if your model gives her yellow legs try adding (black feet) or an equivalent to your prompt. Fur markings can appear on clothing. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.