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.😊This model was 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><h2 id="heading-226">About the artist:</h2>Twitter: <a target="_blank" rel="ugc" href="https://twitter.com/kakao_3percent?lang=en">kakao□単行本5月末発売 (@kakao_3percent) / Twitter</a>Pixiv: <a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/581994">kakao - pixiv</a>Kakao creates hentai manga which means this model is very nsfw.<h2 id="heading-227">Weights &amp; Prompts</h2>The model is activated by the prompt:<pre><code>kakao</code></pre><h3 id="heading-885">Lycoris:</h3>This should be your goto model for most checkpoints, allowing for more flexibility.Use a weight of 1.0, adjust to taste. For reference check the XYZ plot in the examples.<h3 id="heading-884">LoRA:</h3>Only use this with models based on Abyss Orange Mix.Use a weight of 0.9-1.0. Go a bit lower (I used 0.7-0.8) for character loras. As usual I have included XYZ plots for reference.It can be helpful to include "text" in the negative prompts as many of the training images were doujin covers but it is not absolutely necessary.I was pleasently surprised when creating landscapes as they are a bit more surreal but a lot less generic than AOM3 by itself. You can finde 4 images of the same prompt with and without the LoRA above.Please leave a review if you enjoyed this model or have problems with it. This helps me with improving future models and finetuning them in general. Give it a try and throw some images down below! 👇

Kakao - Artist Style (LoRa/Lycoris)

Trained with a learning rate of 3e-4

Files with SHA256: a142869394a4bfdab9989731b59226cf14c22f1db1fd2311bd97706a56bd5ad1