<h3 id="heading-214">Recommendations:</h3>Lora Weight: 0.3-0.7CLIP SKIP 0-1DivineEleganceMix or AbyssOrangeMix3 | models The resolution of the original dataset images leaves much to be desired, so I recommend you to use upscale ( or HighRes fix ) on your images.<h3 id="heading-214">Additional train info:</h3>Trained on: AbyssOrangeMix3.Trained on 20+ anime images.

Schrödinger - Hellsing - LoRA/LyCORIS

A new training approach.Better outfit drawling.Better face drawling.Smaller size.Now LoRA!

Files with SHA256: 874d680a2f74df1b86e55ab768354fe5df21b02a331cd71d1010de9c15cec1e3