Trained on AnyLoraI don't know if i nailed it yet, but this is definitely an improvement over the last version.To get the best results, please read the description below:<ul><li>Recommended weight for V1: 0.6-0.9</li><li>Recommended weight for V2: 0.7-0.85</li><li>Activation word for V1: Power</li><li>Activation word for V2: PowerV2</li><li>Upscale to 1.5</li><li>Using anime SD models is recommended, semi-realistic checkpoints should also work</li></ul>I would appreciate any reviews, positive or negative!I would very much appreciate you sharing your results ^_^If you have any suggestions on what LoRA i should do next, please share them in the commentsEnjoy :)P.S. I also recommend trying out <a target="_blank" rel="ugc" href="https://civarchive.com/models/50025?modelVersionId=65861">this </a>checkpoint, it is absolutely underrated which is a shameIt works pretty good with this LoRA as showcased

Files with SHA256: 42b0233c0e8ed90510f4bfdfdde237fd43a9ddb9d7dc482a469b8699e23b6caf