<h1>Murasaki Shion (Hololive) LoRA</h1>Thank you for deleting my previous LoRA without any warning (I discovered it delection 1 month later) because "Hololive" and "gothic_l*lita" contain a banned word and excluding the domain from wayback archive means that I can't copy paste my old LoRA description (this is annoying for recommended prompts)<h2>01-05-2023/V2 Update:</h2><ul><li>Reduce the model file size to 9MB.</li></ul><ul><li>Use a way lower network dim (8 instead of 128) and Alpha (1 instead of 128) to prevent overfitting</li><li>More flexible</li></ul><ul><li>Rebalanced dataset (I uploaded it)</li><li>More accurate official swimsuit</li><li>Add a new token for each canon outfit (using booru token was a bad idea): <code>ShionDefault</code><code>ShionSwimsuit</code><code>ShionGothic</code></li></ul>V1 is a reupload of my prevous LoRAThis is a LoRA, this mean that you need to update Voldy/AUTOMATIC1111's webui to use it (use <code>git pull</code>) .<h3>Weight:</h3>You won't need to use a lower weight unless you want to use multiple LoRAs<h3>Recommended prompt:</h3>That LoRA can reproduice some of her modelsFor V2:Default outfit:<pre><code>black gloves,single hair bun, witch hat, vertical-striped_shirt,pinstripe_shirt,midriff, crop top,miniskirt, ShionDefault</code></pre>Gothic L*lita :<pre><code>twintails, animal_ear_fluff,gothic_lolita,lolita_fashion,halter dress, cat ears,cat_girl,long dress, halterneck, layered dress,frilled dress, center_frills,detached sleeves, ShionGothic</code></pre>Official Swimsuit :<pre><code>bikini, bikini_skirt, black_bikini,criss-cross halter, swimsuit, ShionSwimsuit</code></pre>For V1:Same thing as V2 but without <code>ShionDefault</code>,<code>ShionSwimsuit</code> and <code>ShionGothic</code><h3>Model used for the example:</h3>V1 examples : AOM 2 and Pastel Mix (model version) .V2 examples : AnythingV4.5

Murasaki Shion (Hololive) (Multiple outfit) (9.1MB + old model reupload)

<pre><code>247 images
6 epochs
4188 steps (batch size:1)
scheduler: cosine
Text encoder learning rate: 1e-5 
Unet learning rate: 1e-3 
max bucket resolution: 512 
clip skip: 2 
dim: 8
alpha: 1 
batch size=1 
Base model: NAI</code></pre>

Files with SHA256: 748ebeefc970e74b4dc0a6fe363959e559f6c05d406afb788bf5ae810997d23f