<h3 id="heading-235">V3: </h3><h3 id="heading-236">High quality and enough versatile. Works wells with both photoreal and anime model. Works best with not too small subject.</h3>Suggested settings: Width:&gt;640 Height: &gt;960 Hires-Fix: &gt;x2 ✔️<h3 id="heading-188">Trigger word: hhayleyy</h3><h3 id="heading-237">outdated V2:</h3>I completely reworked the model. This time is trained in 2 different set of images for a total of 60. One ranked higher with 3x times the weight that the lower rank images. Training done at 768x768 on the base model, this mean that you can use the Lora with evey model. Trigger word: hhayleyy (not really required) Suggested settings: Width:&gt;512 Height: &gt;768 Hires-Fix ✔️

Hayley williams LoRA

I completely reworked the model. This time is trained in 2 different set of images for a total of 60. One ranked higher with 3x times the weight that the lower rank images. Training done at 768x768 on the base model, this mean that you can use the Lora with evey model. Trigger word: hhayleyy (not really required) Suggested settings: Width:&gt;512 Height: &gt;768

Files with SHA256: 208d444a19c7256b262b8a74a78e197d831ee85c990074ffaccd49bee56796c5