<h1 id="heading-2321">3.1-tan | 大婆様  LoRA</h1><p></p><p></p><h3 id="heading-2322">Weight:</h3><p>You won't have to use a lower weight than 1.0 unless you want to use multiple LoRAs</p><p></p><h3 id="heading-2323">Recommended prompt:</h3><p><strong>Default outfit:</strong></p><pre><code>31tanDefault,  hair_bow, juliet_sleeves,  lolita_fashion, long_sleeves,  puffy_sleeves, purple_bow, purple_dress, sitting, brooch, numbered, purple_bowtie, frilled_dress</code></pre><p>Optional prompt for the default outfit:</p><ul><li><p><code>black_pantyhose</code>  or <code>black_thighhighs </code>(some artist draw her with a black pantyhose, some with black thighhighs, some with whites shock,etc...)</p></li><li><p><code>knee_boots, brown_footwear,knee_boots</code></p></li></ul><p></p><p></p><p></p><h3 id="heading-2324">Model used for the example:</h3><p></p><p>V1: YesMix v1.6</p><p></p><p></p>

3.1-tan | 大婆様 (Windows 3.1's OS-tan ) LoRA 

<pre><code>43 images
10 repeats 
6 epochs
2580 steps (batch size:1)
scheduler: cosine
Text encoder learning rate: 1e-5 
Unet learning rate: 0.001</code></pre>

31tanD8V1_e6.safetensors

v1.0 NAI

<p>31tanDefault, hair_bow, juliet_sleeves, lolita_fashion, long_sleeves, puffy_sleeves, purple_bow, purple_dress, sitting, brooch, numbered, purple_bowtie, frilled_dress,black_thighhighs,knee_boots, brown_footwear,</p>

Files with SHA256: 8e613d10dd02888b1c9e56e7ca6236958f76028569b5342f910d33b3a2f58f89