<h2 id="style-lora-of-radishkek-wkfcgvnas">Style LoRA of <a rel="ugc" href="https://www.pixiv.net/en/users/14683662">RadishKek</a></h2><ul><li>Like the style? Give the artist some support!</li></ul><h3 id="drop-a-and-follow-me-if-you-want-more!-1y900s27i">❤️ Drop a 👍 &amp; follow me if you want more!</h3><ul><li>I look forward to your posts, reviews and comments!</li></ul><h3 id="recommendations-mu956261j">🌟 Recommendations</h3><ul><li>Use CFG++ samplers such as Euler CFG++ with a CFG of 1-2.</li><li>If no trigger tags are specified, this LoRA does not need a trigger tag to work!</li><li>Do note that my LoRAs that have been baked on Illu0.1 are compatible with NoobXL's V-Pred models (and any merges / finetunes).</li></ul><h3 id="training-notes-rabz6t5kb">📑 Training Notes</h3><ul><li>Moved to the 'About this version' tab!</li></ul>

RadishKek Style [Illu0.1]

📑 Training Notes<ul><li>Base Model: <a target="_blank" rel="ugc" href="https://civitai.com/models/795765/illustrious-xl">Illustrious-XL</a></li><li>Training Resolution: 1536</li><li>Training Batch Size: 3</li><li>Type: Lora</li><li>DIM / Alpha: 20 / 18</li><li>Conv Dim / Alpha: 18/ 14</li><li>Train On: Unet</li><li>Optimizer: AdamW8</li><li>Scheduler: Rex</li><li>Image Count: 149</li><li>Steps: 2000</li></ul>

Files with SHA256: cfdbc88e198a9c2c15a21dcd6ab700e806b191308c4fc5289f75ca39db7059a1