☕If you like my work, please feel free to donate! <a target="_blank" rel="ugc" href="https://ko-fi.com/notekaga">https://ko-fi.com/notekaga</a><hr /><h2 id="heading-173">XL-animagine-v1</h2><ul><li>Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/260267?modelVersionId=293564">Animagine XL V3</a></li><li>ControlNet is not required for this version</li></ul><pre><code>Recommended weight: 0.7 - 1.0</code></pre>Prompt:<ul><li>Trigger<pre><code>ganbaruzoi</code></pre></li><li>Optional<pre><code>1girl, open mouth, upper body, clenched hands</code></pre></li></ul><hr /><h2 id="heading-174">SD1.5</h2>v4<ul><li>Improvement training images</li><li>Added an image for OpenPose. Recommended to use LoRA and ControlNet(OpenPose) together.</li></ul>v3<ul><li>First release</li></ul><pre><code>Recommended weight: 1.0</code></pre>Prompt: Check the Trigger Words on the rightControlNet settings(SD1.5 only):<pre><code>Preprocessor: none
Model: openpose
Control Weight: 0.8 - 1.0
Control Mode: Balanced</code></pre>

[SDXL/SD1.5] Ganbaruzoi Pose（ぞいの構え/今日も一日がんばるぞい!）

v4.0<ul><li>Improvement training images.</li><li>Added an image for OpenPose. Recommended to use LoRA and OpenPose together.</li><li>v4.0ではモデルの改善に加え、OpenPose用の画像を追加しました。OpenPoseとLoRAを併用するとポーズの安定性が向上するのでお勧めです。（注：フェルンの画像はLoRAのみ使用して生成）</li></ul>

Files with SHA256: 2556a8deafa04e8ff7778003710852ba48da0377f23191a5837b506a67121296