<p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0bf50fd1-5cfb-43d3-be3f-ff2e20d9d7b8/original=true/0bf50fd1-5cfb-43d3-be3f-ff2e20d9d7b8.jpeg" /></p><h3 id="krea2-turbo">Krea2 turbo</h3><p>Uploaded as Version 0.1 for testing Krea2 LoRA generation.</p><h3 id="z-image-turbo">Z-Image turbo</h3><p>Uploaded as Version 0.1 for testing ZIT LoRA generation. All sample images were generated using <a target="_blank" rel="ugc" href="https://github.com/martin-rizzo/ComfyUI-ZImagePowerNodes">Z-Image Power Nodes</a>, with FlashVSR used as the detail enhancer.</p><h3 id="usage">Usage</h3><ul><li><p>Trigger word: jpwmn01</p></li><li><p>Recommended model strength: 1.0 (ZIT), 0.8 (Krea2)</p></li><li><p>CLIP/Text Encoder connection is not required.</p></li></ul><h3 id="disclaimer">Disclaimer</h3><ul><li><p>This model is intended for creating the faces of fictional adult Japanese women.</p></li><li><p>This model does not depict any real person.</p></li><li><p>The creator assumes no responsibility for generated content or misuse of this model.</p></li><li><p>Users are solely responsible for the content they generate with this model.</p></li></ul><h3 id="training-information">Training Information</h3><ul><li><p>Trained with AI-Toolkit using 17 images for 600 steps on an RTX 3060.</p></li><li><p>This LoRA was trained as UNet-only. CLIP / Text Encoder training was disabled.</p></li></ul><p><u>　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　</u></p><p>私の初めてのLoRA作成は、こちらのYouTube動画を参考にしました。（日本人向け）</p><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/yYOXKyPZnzY?rel=1" start="0"></iframe></div><p>ダルトワ★TVさんありがとうございます。</p>

Files with SHA256: 264675a5753d2ea49d3d111f6f2aca7bfbcd63388beaa95fbf5a36de4a86b659