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 <a target="_blank" rel="ugc" href="https://github.com/dustysys/ddetailer">DDetailer</a> extension, which pretty much automates the face inpainting workflow I often do.) I've used <a target="_blank" rel="ugc" href="https://civarchive.com/models/6424/chilloutmix">ChilloutMix</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/17449/level4">Level4</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/9052/lofi">LOFI</a>, and <a target="_blank" rel="ugc" href="https://civarchive.com/models/20282/henmixreal">henmix_real</a>.

Eunbi

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.

Files with SHA256: 28a1971f518b9070f853b687895454f918d690325d02b15247cbf9737c48bf43