Lora trained of a bunch of my style Lora's, turned out quite nice!

-- v2.0 --

Main Tag: th3-4lph4b3t-t4g

-- v1.0 --

had to make a new one as the v1.0 tag was getting flagged for having k1d in its trigger tag, so i've removed it from the model. It still kinda works without it, but if you are generating locally use 'the-4lphab3t-k1d'

How I use it:

Tool: Forge

Checkpoint: Midnight v20 baked vae

Steps: 20

CFG Scale: 1.3-2

Size: 940x1216 (or something similar)

I then img2img at 0.4 denoising strength, with the largest size to 2048, and the Lora's strength down to around 0.5.

Then ADetailer the bejesus out of it (specifically with mask dilation around 40-60, inpainting mask blur around 30-50, and denoising around 0.3-0.6).