Type | |
Stats | 271 151 26 |
Reviews | (45) |
Published | May 30, 2024 |
Base Model | |
Training | Epochs: 30 |
Usage Tips | Clip Skip: 2 Strength: 1 |
Trigger Words | sumi-e |
Hash | AutoV2 F68AE7AB78 |
Lora style focused on producing flowy inky works inspired by sumi-e. Works best with the original PonyXL model.
The weight that I found worked best for me was 1.0 to 1.5. Higher weights increase the flowiness, but might affect anatomy. Recommended to increase weight for derivative PonyXL models
Trigger word is 'sumi-e' adding 'monochrome' helps as well.
Tested on two other models. is subdued on autismmix, but works decently enough. animeboysxlV3 forgoing quality tags really brings out sumi-e quality, but adding them produces nice images as well.
I've also started a patreon with a currently ongoing public poll for what my next Lora will be, tips are appreciated, but even voting in the poll is much appreciated. https://www.patreon.com/ArtificalisAnima - Warning 18+