Verified: a year ago
SafeTensor
Type | |
Stats | 308 0 |
Reviews | (46) |
Published | Apr 29, 2024 |
Base Model | |
Training | Steps: 2,000 Epochs: 10 |
Usage Tips | Clip Skip: 2 |
Hash | AutoV2 B750DAC291 |
LoRA created from 303 images from various publications with art by Masami:
Recommended weight 0.7 to 0.8 depending on your model and prompt.
No trigger word is needed, but you can use aoi_masami if you want.
Due to artist influence the images are biased towards certain style of characters and will lose strength if you try prompts too different.