<h3 id="greaternoobai-v-pred-or-ponydiffusion-or-sd-1.5">-&gt;NoobAI V-Pred | <a target="_blank" rel="ugc" href="https://civarchive.com/models/101626?modelVersionId=487812">PonyDiffusion </a>| <a target="_blank" rel="ugc" href="https://civarchive.com/models/101626?modelVersionId=108788">SD 1.5</a></h3><hr />Please, check the description, there is a little bit of useful information.<hr />Inеtroduction:This LoRA is supposed to represent Jadf's artstyle.Please, be sure to use the same positive and negative quality prompt for better result.<hr />Compatibility:<ul><li>Humans: great</li><li>Anthros: great</li><li>Ponies: great</li><li>Multiple characters: great</li><li>Character LoRAs; great</li><li>Unique characters: great</li></ul><hr />Recommendations:<ul><li>Trigger word - jadf (v4+)</li><li>Trigger word - jdf (v3)</li><li>1.0 emphasis</li><li>Clip Skip 1</li><li>CFG 5</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/833294/noobai-xl-nai-xl">NoobAI 1.0 V-Pred </a>for generations (Main)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/833294/noobai-xl-nai-xl">NoobAI 1.0 Eps</a> for generations (Alternative)</li><li><code>masterpiece, best quality, highres, absurdres</code> in positives</li><li><code>worst aesthetic, worst quality, low quality, bad quality, lowres, flat color</code> in negatives</li><li>+ <code>colorful, saturated, red theme, blue theme</code> for CIvitAI generations</li><li>CFG Rescale 0.3 - 0.4 (if you're using v-pred version)</li></ul>Use anything else in negatives only if you want to avoid or remove something from the image. For example, you don't want to see doors - "door" in negative. Style will look much better without garbage in negative prompt. Just try it.<hr />Characters (v4+):<ul><li>Jadf-tan<ul><li><code>black hair, very long hair, blunt bangs, hime cut, red hairband, yellow eyes</code></li></ul></li></ul><span style="background-color:rgb(26, 27, 30);color:rgb(134, 142, 150);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">There is still not so much images of her, but character is now working, at least. I hope you'll like this change, and of course, i hope there will be more art of her in the future.<hr />Credits:Trained on NoobAI 1.0 V-Pred. Dataset of 200 pictures (v1), 30 epochs, Clip Skip - 1 Trained on NoobAI 1.0 V-Pred. Dataset of 300 pictures (v2), 40 epochs, Clip Skip - 1 Trained on NoobAI 1.0 V-Pred. Dataset of 260 pictures (v3), 40 epochs, Clip Skip - 1 Trained on NoobAI 1.0 V-Pred. Dataset of 550 pictures (v4). 30 epochs. Clip Skip - 1 Trained on NoobAI 1.0 V-Pred. Dataset of 600 pictures (v5). 30 epochs. Clip Skip - 1 Trained on NoobAI 1.0 V-Pred. Dataset of 600 pictures (v5). 30 epochs. Clip Skip - 1Really big thanks to:<ul><li><a target="_blank" rel="ugc" href="https://jadf.fanbox.cc">Jadf </a>for beautiful artwork</li><li>Some good folks from Discord server</li><li>You, for reading, downloading, liking and reviewing this LoRA</li></ul>

Jadf - Style LoRA - NoobAI

What's new?<ol><li>Expanded dataset up to 300 images</li><li>Better style consistency in general</li><li>Better lighting and shadows</li><li>Improved color, contrast and saturation</li><li>Brighter images, need further training</li></ol>

Files with SHA256: eed7297f1de20ed5950f9214ea989d0c688d73c41b42ab3379acd5f240ca16e2