Negative values remove makeup, positive values add. Recommended range of values: [-3, 3]
You can find detailed information about the versions in these articles:
Description
The ai toolkit was used for training. Training parameters:
resolution: 256
rank: 4
steps: 120
lr: 7.0e-05
positive_prompt: "Dramatic smoky or colorful eyeshadow, bold lipstick (red, purple, dark), heavy eyeliner, false lashes, high color contrast"
negative_prompt: "Natural skin, no eyeshadow, nude or no lipstick, minimal enhancement"
target_class: "person, makeup"
anchor_class: ""FAQ
Comments (1)
Most people probably underestimate this LoRa.
In my opinion, it effectively solve the issue of inflated character makeup values caused by the raw training data.
Yes, even the emphasis of prompts could not manage this situation.