V1:

A LoRA for JMG's Style based on Any-L.

Shouldn't need any trigger words, however adding 'jmg' or 'jmg style', may force 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 over represents large proportions, so use some negatives.

For best results, or results similar to mine, please use Any models or a similar anime-style model. Additionally, it is most recommended to use badv3/EasyNegative textual inversions.

Should work fine with other LoRAs.

Examples done using CounterfeitV3.0. 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

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