<p>Hey All, presenting my <strong>Ann Possible LoRA</strong> from <em>Kim Possible</em>.</p><p>Ann Possible is Kim Possible's mother and a brilliant scientist. I always loved her design and so decided to give it a whirl</p><h3 id="base-model">Base Model</h3><p><strong>Anima 1.0</strong> — Base checkpoint (<code>anima-base-v1.0</code>).</p><h3 id="recommended-weight">Recommended Weight</h3><pre><code>0.9 (0.8 or below if it doesn't look good with NSFW)</code></pre><h3 id="trigger-word">Trigger Word</h3><pre><code>annp</code></pre><h3 id="style">Style</h3><pre><code>2d animation, cel shading, flat colors,</code></pre><h3 id="appearance">Appearance</h3><pre><code>red hair, short hair, bob cut, blue eyes,</code></pre><h3 id="default-clothes">Default Clothes</h3><pre><code>white lab coat with long sleeves, purple shirt,purple skirt, belt with belt buckle, </code></pre><h3 id="optional-full-body-footwear">Optional — Full Body / Footwear</h3><pre><code>white high heels</code></pre><p>The appearance and default outfit tags can be used separately depending on what you want to generate. The LoRA should also work with different outfits while retaining Ann's identity.</p><h3 id="suggested-generation-settings">Suggested Generation Settings</h3><p>My testing was done using a <strong>Turbo LoRA</strong> with:</p><ul><li><p>LoRA weight: <strong>0.9</strong></p></li><li><p>Sampler: <strong>Euler a</strong></p></li><li><p>Scheduler: <strong>Simple</strong></p></li><li><p>Steps: <strong>12</strong></p></li><li><p>CFG: <strong>2.5</strong></p></li></ul><p>You can refer to my images for more examples. I have tried to tag the training images with accurate metadata and seeds.</p>

Files with SHA256: cf0bf68e87e8e8f3f96132798924d092d6fa2481e1c90efffee9ba3e52b3eed2