Verified: a year ago
SafeTensor
Type | |
Stats | 514 5,081 |
Reviews | (110) |
Published | Nov 13, 2023 |
Base Model | |
Training | Steps: 2,000 Epochs: 8 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Trigger Words | Galarian Ponyta |
Hash | AutoV2 EAD1A44480 |
Galarian Ponyta LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Works well, add (large fluffy hair) to really bring out the fluffy hair, though it's not necessary. Fluff can get out of control at times. Horn color and striping is closer to Galarian Rapidash than Galarian Ponyta. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on a mixed male/female dataset.