A character model 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>I recommend using a weight of 1.0. Check the examples for an XYZ plot of different weights.Check out original art here: <a target="_blank" rel="ugc" href="https://twitter.com/00_Homura/status/1290122405613129728/photo/3">A Yorra-centric look at the Zirca Region / Twitter</a>Or more NSFW: <a target="_blank" rel="ugc" href="https://www.newgrounds.com/art/view/thiccwithaq/princess">Princess by ThiccwithaQ on Newgrounds</a>Some helpful prompts to get the details and outfit right:<ul><li>(green eyes, green lips)</li><li>(thigh strap, single thighhigh,purple high waist shorts, black sweater , long sleeves, single glove:1.2)</li></ul>Note that stable diffusion occassionally struggles with coloring parts individually or will mirror everything even when only training with non-mirrored images. The glove in particular has a tendency to either be the wrong color or bleed into the rest if the image. This could be fixed with more training steps at the cost of flexibility.I have also included samples on how the model meshes with my Style LoRA. The style LoRA for ThiccWithaQ/Nyantcha works really well at replicating the original art.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!

Files with SHA256: 06a3fd941b396941d94b173bda4d699c611694cdce59d548bef10d28d0b8059d