<p>Hey All, presenting my second LoRA – <strong>Jennifer Peenman AKA Gorgonzola</strong> from the hit 90’s cartoon – <em>The MASK Animated Series</em>.<br /><a target="_new" rel="ugc" href="https://the-mask.fandom.com/wiki/Jennifer">Jennifer – The Mask Wiki</a></p><p>It is one of my favourite series and I always loved her design.</p><p>I have kept a small download fee to help me gather some buzz for online LoRA training and experimentation. It was really tough getting this right, so I would really appreciate your feedback and, of course, any pictures you generate with the LoRA!</p><h3 id="base-model">Base Model</h3><p><strong>Anima 1.0</strong> — Base checkpoint (<code>anima-base-v1.0</code>). <strong>Not</strong> the Aesthetic or Turbo variants.</p><h3 id="recommended-weight">Recommended Weight</h3><pre><code>0.9</code></pre><h3 id="style-tags">Style Tags</h3><p>These can be added when you want to emphasize the original retro animated-series appearance:</p><pre><code>2d animation, retro artstyle, cel shading</code></pre><p>You can remove these if you want the character rendered in a more modern/non-retro style.</p><h3 id="trigger-word-and-locked-appearance">Trigger Word &amp; Locked Appearance</h3><pre><code>jenni_mask,blonde hair, medium hair, black eyes, makeup, red lips</code></pre><h3 id="default-outfit">Default Outfit</h3><pre><code>yellow turtleneck sweater, long red and black coat, purple pants, black belt, gold medallion necklace, open coat</code></pre><h3 id="optional-full-body-footwear">Optional — Full Body / Footwear</h3><p>If her footwear doesn't come out correctly, especially in full-body generations, try:</p><pre><code>black footwear, high heels</code></pre><h3 id="known-quirk">Known Quirk</h3><p>Some of the training data also contained <strong>Stanley Ipkiss</strong>, so he can be generated with below tags</p><p>If you want to experiment with him, try:</p><pre><code>1boy, brown hair, blue suit</code></pre><p>However, <strong>this is not a dedicated Stanley LoRA</strong>, so don't expect consistent results.</p><h3 id="suggested-generation-settings">Suggested Generation Settings</h3><p>My testing was done using below with turbo Lora</p><ul><li><p><strong>Sampler:</strong> Euler a</p></li><li><p><strong>Scheduler:</strong> Simple</p></li><li><p><strong>Steps:</strong> 12</p></li><li><p><strong>CFG:</strong> 2.5</p></li><li><p><strong>LoRA weight:</strong> 0.9</p></li></ul><p>You can refer my images for more, i have tried tagging accurate metadata and seed</p><p></p>

Files with SHA256: d6efbcaaf66d55d078aaf1cd7b30f8d2520b89bbd889d63b6f2bde04d9277f7f