<h3 id="heading-800">V2.0</h3>This update makes the model a whole lot more flexible by training on NAI with small training steps.Use a weight of 0.7-1. Check the XYZ plot for more details.The model details contains 2 helpful prompt collection for getting the usual hairstyle and clothing respectively.Unlike v1.0 this model works very well with other style LoRA. To get depictions closer to the original I recommend combining this with my <a target="_blank" rel="ugc" href="https://civarchive.com/models/62561/hyocorou-artist-style-or-aom3">Hyocorou Style LoRA</a> at 0.5 weight.<h3 id="heading-801">V1.0</h3>A character model trained for AOM3 using the collab/guide by holostrawberry <a target="_blank" rel="ugc" href="https://civarchive.com/models/22530/guide-make-your-own-loras-easy-and-free">[Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai</a>This model is nsfw and has a bias towards topless depictions.Check out the character at 419681I recommend using a weight of 0.85-1.As this is a hyocorou original character with no fanart this lora also affects the artstyle. To combine the model with other styles a weight around 0.85 works best (I have included quite a few examples). At 0.6 and below there is little resemblance as can be seen in the XYZ plot.For the classic outfit use these or similar prompts:side braid, headband, hair ornament, (highleg panties, highleg, shorts,thighhighs:1.2), off-shoulder jacket, oversized jacket, bare shoulders, tube top, red ribbon, hair ribbon, puffy sleevesFor the alternate hairstyle twintails works more often than not.Please leave a review if you enjoyed this Lora or have problems with it. I'd also be interested in how the lora behaves with other base checkpoints so why don't you give it a try and throw some images down below!

Amnero - Kyouka Jinrui Amunero | Character Lora

Refined training on the same dataset

Files with SHA256: fa6ae39279d59483fbf2d43414438c30fc859999623dd83feab41184f52c9d01