<h1 id="nagatoro-v1-v8ebcofjl"><strong>Nagatoro V1</strong></h1><p>This model aims to help in producing images of Nagatoro, from "Ijiranaide, nagatoro-san". It was trained on 22 images, for 10 epochs, and it is intended to work with pony xl models, in particoular my "Blue-tear" model.</p><p></p><h2 id="how-to-use-it-6oz3wvfjm">How to use it?</h2><p>You can pretty much plug and play the model.</p><p>To activate it use the keyword: "N4G4T0R0".</p><p>Then you can describe the desired attire, and scene.</p><p></p><hr /><h3 id="!!important!!-v0nrae87y"><span style="color:#fa5252">!!</span><u><span style="color:#fa5252">Important</span></u><span style="color:#fa5252">!!</span></h3><p><span style="color:#868e96">The model was trained omitting the keyword "1girl" so, when you use this lora, try to not use this keyword cause it's not needed, and might make the generation worse</span></p><h3 id="example-of-positive-prompt-70x720a62">Example of Positive Prompt</h3><p>Score_9, score_8_up, score_7_up BREAK &lt;Nagatoro:1&gt; N4G4T0R0, white shirt, upper body, cowboy shot</p><hr /><p></p><h2 id="what-are-the-suggested-settings-2j0gmsvsy">What are the suggested settings?</h2><p>Lora weight: 0.6 ~ 1</p><p></p><p>Lowering the weight reduce the impact of the lora on the style, but "some times" require more keywords, for example lowering at 0.7 or below makes nagatoro lose the "dark_skin".</p><p> </p><p>Those are some keywords that can help obtaining the standard nagatoro:</p><pre><code>dark_skin, long hair, black hair, brown eyes, hairclip, earclip</code></pre><p></p><hr /><p>This model works decently with manga style, just add (at the end of the prompt):</p><pre><code>greyscale, comic, screentone</code></pre><p>But if you are interested in generating those kind of images, you might wanna get familiar with some additional tag for image composition (ie. koma tags): </p><pre><code>https://danbooru.donmai.us/wiki_pages/tag_group%3Aimage_composition</code></pre><hr /><p></p><h2 id="extra-tips-xqktcg8g4">Extra tips</h2><p>The model was trained on 1024*1024 images, so some prompts might struggle with some thinner resolution like 768x1344, but work perfectly fine with wider one like 832*1216.</p><p></p><p>You can even use the "nagatoro" tag, with "N4G4T0R0" and have an even better generation, but in those cases you should sensibly reduce the lora weight (0.6).</p><p></p><hr /><p></p><h2 id="does-it-support-nsfw-yyqcbul3s">Does it support nsfw?</h2><p>Yes, it does. That said, just because it can do it, it doesn't mean you should do it.</p><p></p>

Nagatoro | Pony Character Lora

<p>This is a test version for pony training. It is better than expected, but it could be improved so i might release a v2 in the future.</p>

Files with SHA256: f80e685458a0eba489eb0391b4bc2fef1f4acf3cec199d2a2a22e3e9ba6a0581