Remember to use the trigger word kwoneunbi. Use LORA weight 1 and Hires fix with latent bicubic antialiased, 20 steps, 0.4-0.6 denoising strength, and 1.25x upscale. (I've also been the DDetailer extension, which pretty much automates the face inpainting workflow I often do.) I've used ChilloutMix, Level4, LOFI, and henmix_real.
Description
There are a few weird clothing artifacts sometimes from some overfit clothes, might have to weight outfits accordingly. Again, I'll rework the dataset and retrain because it's pretty good otherwise.