If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊You can also buy me a Coffee ☕<a target="_blank" rel="ugc" href="https://emojipedia.org/hot-beverage"> </a>at <a target="_blank" rel="ugc" href="https://ko-fi.com/stickyricky">https://ko-fi.com/stickyricky</a>These models were trained 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>Edit: As I can't find NAI anywhere on civit: <a target="_blank" rel="ugc" href="https://huggingface.co/a1079602570/animefull-final-pruned/blob/main/model.ckpt">https://huggingface.co/a1079602570/animefull-final-pruned/blob/main/model.ckpt</a>This is a really vanilla checkpoint that I train all my models on. <h3 id="heading-1473">About the artist:</h3>Hyocorou has a really interesting and unique artstyle that is hard to get right. Check them out here: <a target="_blank" rel="ugc" href="https://twitter.com/hyocorou?lang=en">ひょころー (@hyocorou) / Twitter</a>or check out 485937. As they create hentai art you can expect nsfw outputs.<h3 id="heading-1474">Weights &amp; Prompts</h3>v2.0 (LoCon):Use a weight of 0.8-1.4. I stayed in the range 0.9-1.0. That includes most character LoRA. Be aware that even the most well-trained charater LoRA can conflict with the style.LoCon:Use a weight of 1.0 or lower. When used with character LoRA with their own artstyle (or my Amunero LoRA) you should go a lot lower.LoRA:This model was trained on AOM3 and is worse than the new LoCon version in my opinion!A weight of 1 works when used by itself. For most character lora I used 0.75 but it's all about experimentation. Sometimes a small change in the number of sampling steps or just going up to 0.8 can have massive influence on the output.Note that this model struggles more with hands than you might be used to and you will regularly need to go over the image in inpaint or edit it manually. I can only guess that this is because of the massive difference between male and female characters drawn by hyocorou.While hyocorou mostly makes nsfw content in my opinion the soft look works surprisingly well for landscapes.Please leave a review if you enjoyed this model or have problems with it. I'd also be interested in how the model behaves with other base checkpoints, so why don't you give it a try and throw some images down below! 👇

Files with SHA256: a770591069e27afa13f67c28d0098d826dae22437587133df6ed5c889c955285