<h1>Kakudate Karin (Blue Archive) LoRA</h1>I'm doing some experiments with low net dim LoRA (8 net dim / 1 Alpha) and I'm surprised at how faithful it is. (and it seem to be more flexible than high net dim LoRA)This is a LoRA, this mean that you need to update Voldy/AUTOMATIC1111's webui to use it (use <code>git pull</code>) .That LoRA does not have a particular trigger (except the default <code>&lt;lora:LoRaName:1&gt;</code>).<h2>Weight:</h2>I only tested it at weight <code>1.0</code><h2>Recommended prompt:</h2>For more accurate result I recommand to use:<code>very long hair</code> (I didn't pruned that tag in the dataset to make it easier to change her hairstyle)<code>dark skin</code> (I pruned that tag in the dataset but for some reason it can happen that it generate a lighter skinned version of her if you don't use it)That LoRA can also replicate some of her canon outfit:Maid Uniform:<pre><code>black_dress, blue_bowtie, halo, karin_(blue_archive),maid,white_gloves, maid_headdress, puffy_short_sleeves, white_apron, white_pantyhose,maid_apron, pleated_dress, frilled_dress,very long hair,dark_skin</code></pre>Bunny Girl:<pre><code>black_leotard, blue_bowtie, fishnet_pantyhose,karin_(bunny)_(blue_archive), number_tattoo, playboy_bunny, rabbit_ears, ponytail,dark_skin,very long hair</code></pre>School Uniform :<pre><code>blue_cardigan, blue_bowtie, collared_shirt, halo, karin_(school_uniform)_(blue_archive), pleated_skirt, school_uniform, stud_earrings,long_sleeves, black_skirt ,dark skin,very long hair</code></pre><h2>Model used for the example:</h2>AnythingV4.5<h3></h3>That character is owned by Nexon and Yostar.

Kakudate Karin (Blue Archive) LoRA (multiple outfit) [9.1 MB]

Training settings:<pre><code>109 images
5 repeats 
6 epochs
3270 steps (batch size:1)
Text encoder learning rate: 1e-5 
Unet learning rate: 1e-3 
Max bucket resolution: 512 
Clip skip: 2 
Network dim: 8
Alpha: 1 
scheduler: cosine
Batch size=1 
Base model: NAI</code></pre>

Files with SHA256: 9c05b3d297afb9fe3a98a0debcb5bc527859886bc12ace061428949895a0f4a1