Please do not use this model online to generate any NSFW content; feel free to download it and enjoy it privately.

——————
This style LoRA was trained using 119 images.

For best results, use a weight of 0.7–1.0 when using this LoRA alone. When combining it with other style LoRAs, feel free to lower the weight as needed.

Prompts

@milkteasfisdisstyle

V1.5➡️With 3,000 more steps under its belt, the quality took a massive leap forward and the artist's style fidelity is way higher now. Moving past the 1.0 UN version, this release is finally a fully baked, mature style LoRA.

V1.0➡️Trained using anima_baseV1，it didn't quite capture the artist's skin texture, so this is just a UN version, but I think this style LoRA still has its own unique strengths to offer.