V1:

A LoRA for Hirokix's Style based on YesMix.

Shouldn't need any trigger words, however adding 'roki_hirokix style' forces the style more. Works best at weight 1.0 and using 1girl. Clip Skip 2, however it is not required to generate good images. Trained on booru tags. Good SFW & NSFW.
Currently overfit on images with text, negatives needed if using >0.8 weight.

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

Download the example images and place into PNG Info of UI to get exact details. I use 'Highres. Fix' and 'Additional Networks'.

Should work fine with other LoRAs and models.

Examples done using YesMIx. It still takes some work to get a high detail perfection.

Usage:

• CFG Scale: 7-9

• LoRA Weight: 0.4-0.8, 1.0 may give text/comic features, so add negatives

• Should work fine for less detailed prompts, hands need some work

• Trigger: roki_hirokix style