This model is trained from a merge of the following models:<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/260267?modelVersionId=403131">Animagine3.1</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/410737?modelVersionId=662070">Neta Art XL</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/564727/leekai">LeekAI</a></li></ul>The dataset was collected from Danbooru and Rule 34. Major tags have been converted to Danbooru tags. The model's NSFW training is still under development, so please look forward to future updates.Providing as detailed prompts as possible will yield better results.For LoRA training, "<a target="_blank" rel="ugc" href="https://civarchive.com/models/399873/kohaku-xl-epsilon">Kohaku-XL Epsilon rev2</a>" is used as the base model (other models can also be used).Prompting Guide<ul><li>1girl/1boy/2girls..., character name, copyright, by artist name, general tags, very aesthetic, amazing quality, best quality</li></ul>Negative Prompts (Example)<ul><li>lowres, (worst quality, low quality:1.4), normal quality, bad anatomy, blurry, cropped, text, jpeg artifacts, signature, watermark, username, artist name</li></ul>Thank you to the creators of each model.License<a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a>Support☕ <a target="_blank" rel="ugc" href="https://ko-fi.com/sfa837348">https://ko-fi.com/sfa837348</a>

Files with SHA256: 42d4b21e1a681ce0265693593306cf33ed8c987ff320f23f26265ec467692f3e