Artist Style LoRA for Peritian.

Description:

This is an artist style LoRA of Peritian. Out of all of the models I’ve tested, NovaFurry v9b and WAI v14 tend to work the best. Poor eye detail, style matching, and weaker inferencing seem to happen more often with Banana and Plantmilk.

Training Settings:

• Optimizer: Prodigy / Cosine

• Base Model: Illustrious v1.1

• Trigger Word(s): p3r1t1an

• Training Steps/Epochs: 3938/14 (Clip skip 2)

• Dataset Size: 210

• Recommended Weight: 0.8-1.3 (1.0)

Sampler Settings:

• Steps: 30

• CFG: 4.5

• Sampler: Euler_a

Positive Styling:

flat colors, cinematic

Suggested Resources:

https://civitai.com/models/1001945 - (Detail Slider IL)

https://civitai.com/models/827184 - WAI v14

or

https://civitai.com/models/503815 - NovaFurry - v9b (I included multiple different model comparisons using WAI, Nova, and Plantmilk and I suggest the new Nova v9b or WAI v14 for most gens)

Please remember to follow/support the artist if possible.