V1:

A LoRA for Yoshiie's Style based on YesMix.

Shouldn't need any trigger words, however adding 'yoshiie' or 'yoshiie style', forces the style more. Works best at weight 0.8-1.0. Clip Skip 2, however it is not required to generate good images. Trained on booru tags. Good SFW & NSFW. Currently images with text and greyscale are over represented, so use some negatives.

For best results, or results similar to mine, please use YesMix. Additionally, it is most recommended to use EasyNegative textual inversion.

Should work fine with other LoRAs.

Examples done using YesMix. Follow prompts to attempt replication and use given negatives for better generations.

Usage:

• CFG Scale: 7-9

• LoRA Weight: 0.6-0.8, 1.0 may default to giving text or greyscale, so add negatives

• Should work fine for less detailed prompts. High-res fix is highly recommended

• Trigger: yoshiie style