Verified: a year ago
SafeTensor
Type | |
Stats | 447 2,457 |
Reviews | (71) |
Published | Oct 26, 2023 |
Base Model | |
Training | Steps: 2,000 Epochs: 8 |
Usage Tips | Clip Skip: 1 |
Trigger Words | Quilava |
Hash | AutoV2 AD0F938C6D |
Qulava LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Very consistent. YiffyMix tries to add a tail, adding (tail) to your negative will fix that. Add (flaming hair) to your prompt to get Quilava's fire plumes as a hairstyle. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.