Welcome to KayWaii XL!Although the name was taken from my previous SD 1.5 model, this model is not a complete reboot of KayWaii, it’s more like an attempt to recreate it with the current resources available. This model is built on top of AutismMix Confetti (I know I’m more known as an Animagine XL creator lately and <s>as a part of the actual Animagine team</s>, but I want to try something different.)<h3 id="changelog-u2ux3rub9">Changelog</h3><ul><li>v1.2: More throughout dataset cleaning, re-tagged dataset with better tagger, improve LoRA capability.</li></ul><ul><li>v1.1: Updating dataset and improving training settings so the maximum epoch is usable.</li><li>v1.0: Initial release</li></ul><h2 id="how-to-use-the-model-bpmxyorox">How to use the model</h2><h3 id="prompting-das4f0f9c">Prompting</h3><ul><li>Use this prompt format to help you get better results:</li></ul><pre><code>1girl/1boy, (describe what you want, using danbooru tags is recommended), score_9, score_8_up,</code></pre><ul><li>Use this negative prompt format:</li></ul><pre><code>score_4_up, score_5_up, extra digits, fewer digits, (things you want to remove, using danbooru tags is recommended)</code></pre><h3 id="settings-ltu1e72pb">Settings</h3><ul><li>Euler a</li><li>Steps 25-28</li><li>CFG 5-7</li><li>The sweet spot is around 25 steps with CFG 5.</li></ul><h2 id="training-configurations-uixgrbpry">Training configurations</h2><ul><li>Version: v1.2</li><li>Training method: LoRA training, then merging the trained LoRA into AutismMix Confetti.</li><li>Dataset size: 28,546 images.</li><li>Epoch: 10</li></ul>(I will not give more details in public, since both Pony base and AutismMix did not care to give training details too. But feel free to DM me to ask something about it.)PonyDiffusion XL v6 and its derivatives fall under the <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> license. (Hey astralite, you should publish training details you know if you’re using this license.)===<a target="_blank" rel="ugc" href="https://tensor.art/u/699664973248342228">https://tensor.art/u/699664973248342228</a>

KayWaii XL

Training method: LoRA training and mergingTraining data: 23,646 imagesEpoch: 7

Files with SHA256: bf42d560608b1dab4d8c383d8addabda7a48f99d2555b7e671931ae8d2c73026