<h2>Resource used: <a target="_blank" rel="ugc" href="https://civarchive.com/models/22530">https://civarchive.com/models/22530</a></h2><h3>I will no longer be accepting any more requests, thank you for supporting my models!</h3>Your characters may have insufficient training data! Click <a target="_blank" rel="ugc" href="https://docs.google.com/document/d/1CXxdxT5zNdAhLO58ggvYIQjp3Ll5-IgysHmROJBKpas/view?usp=sharing">here</a>.Weight: 1.0Trigger + Appearance: <code>neopolitan, heterochromia, brown eyes, pink eyes</code>Default Outfit: <code>white jacket, cropped jacket, black leotard, leotard under clothes, pants, belt</code>You may add <code>bowler hat</code> if you want, but I can't guarantee a perfect hat will come out.If you're lucky, you can have her in just a <code>leotard</code> if you put something like <code>(jacket, long sleeves, gloves:1.3)</code> in the negative prompt. You may also remove her leotard under her jacket if you put <code>(leotard:1.3)</code> in the negative prompt.There's also an experimental version which uses AI-generated images (given by the requester) of another Neopolitan model as part of the training dataset, so feel free to try that out if you want.I've accumulated 343 responses, which is about double the last time I reported this number? It's actually a bit less than 343 because I haven't cleared the requests that I already fulfilled. I think I'll be giving Google Colab a break, I've hit the usage limit a couple times, so I'll be collecting and curating datasets in the meantime.The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler.

Neopolitan | RWBY

Initial release. This version uses AI-generated images as part of the training dataset.

rwby_neopolitan-10.safetensors

v1.0-AI

v1.0-NoAI

&lt;h2&gt;Resource used: &lt;a target=&#34;_blank&#34; rel=&#34;ugc&#34; href=&#34;https://civitai.com/models/22530&#34;&gt;https://civitai.com/models/22530&lt;/a&gt;&lt;/h2&gt;&lt;h3&gt;I will no longer be accepting any more requests, thank you for supporting my models!&lt;/h3&gt;&lt;p&gt;&lt;strong&gt;Your characters may have insufficient training data! Click &lt;/strong&gt;&lt;a target=&#34;_blank&#34; rel=&#34;ugc&#34; href=&#34;https://docs.google.com/document/d/1CXxdxT5zNdAhLO58ggvYIQjp3Ll5-IgysHmROJBKpas/view?usp=sharing&#34;&gt;&lt;strong&gt;here&lt;/strong&gt;&lt;/a&gt;&lt;strong&gt;.&lt;/strong&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Weight:&lt;/strong&gt; 1.0&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Trigger + Appearance:&lt;/strong&gt; &lt;code&gt;neopolitan, heterochromia, brown eyes, pink eyes&lt;/code&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Default Outfit:&lt;/strong&gt; &lt;code&gt;white jacket, cropped jacket, black leotard, leotard under clothes, pants, belt&lt;/code&gt;&lt;/p&gt;&lt;p&gt;You may add &lt;code&gt;bowler hat&lt;/code&gt; if you want, but I can&#39;t guarantee a perfect hat will come out.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;If you&#39;re lucky,&lt;/strong&gt; you can have her in just a &lt;code&gt;leotard&lt;/code&gt; if you put something like &lt;code&gt;(jacket, long sleeves, gloves:1.3)&lt;/code&gt; in the negative prompt. You may also remove her leotard under her jacket if you put &lt;code&gt;(leotard:1.3)&lt;/code&gt; in the negative prompt.&lt;/p&gt;&lt;p&gt;There&#39;s also an experimental version which uses AI-generated images (given by the requester) of another Neopolitan model as part of the training dataset, so feel free to try that out if you want.&lt;/p&gt;&lt;p&gt;I&#39;ve accumulated 343 responses, which is about double the last time I reported this number? It&#39;s actually a bit less than 343 because I haven&#39;t cleared the requests that I already fulfilled. I think I&#39;ll be giving Google Colab a break, I&#39;ve hit the usage limit a couple times, so I&#39;ll be collecting and curating datasets in the meantime.&lt;/p&gt;&lt;p&gt;The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler.&lt;/p&gt;

&lt;p&gt;Initial release. This version uses AI-generated images as part of the training dataset.&lt;/p&gt;

Files with SHA256: b1592aaff383d8e39d3a5c72abbc1ba1c7b7b3934fe381410f5e09e82f0af21d