Hey All, presenting my Daphne Blake LoRA from Scooby-Doo! Return to Zombie Island.<a target="_new" rel="ugc" href="https://en.wikipedia.org/wiki/Scooby-Doo!_Return_to_Zombie_Island">Scooby-Doo! Return to Zombie Island – Wikipedia</a><h2 id="update:-moss-version">UPDATE: MOSS VERSION</h2>Hey all! This is my first attempt at creating a MOSS LoRA, so I'd love to see your generations and hear your feedback!<h3 id="recommended-strength">Recommended Strength</h3><pre><code>0.9</code></pre><h3 id="trigger-word">Trigger Word</h3><pre><code>daphnertzi</code></pre><h3 id="default-outfit">Default Outfit</h3><pre><code>green scarf around neck, purple dress, pink pantyhose, purple high heels</code></pre>You can refer to my example images for reference. I've used a pruned model with the settings below due to my system's hardware limitations.However, if your system allows it, I'd recommend trying the following generation settings with the full model:<h3 id="recommended-generation-settings">Recommended Generation Settings</h3><ul><li>Sampler: er_sde</li><li>Scheduler: beta</li><li>CFG: 3.0</li><li>Steps: 50</li></ul><h3 id="my-settings">My Settings</h3><ul><li>Sampler: er_sde</li><li>Scheduler: beta</li><li>CFG: 3.0</li><li>Steps: 25 (to save time)</li></ul>I haven't tested this LoRA with the Turbo model yet, so I'd be interested to hear how it performs if anyone gives it a try. Feedback and generation examples are always welcome!_____________________________________________________________________________________________<h3 id="base-models">Base Models</h3>Anima 1.0 — Base checkpoint (<code>anima-base-v1.0</code>). Not the Aesthetic or Turbo variants.Illustrious — Trained on <code>WAI-illustrious-SDXL_v11</code><h3 id="recommended-weight">Recommended Weight</h3>Anima<pre><code>0.9</code></pre>Illustrious<pre><code>0.8</code></pre><h3 id="trigger-word">Trigger Word</h3><pre><code>daphnertzi</code></pre><h3 id="style-(anima-and-illustrious)">Style (Anima and Illustrious)</h3><pre><code>2d animation, cel shading, flat colors</code></pre><h3 id="appearance-(anima-and-illustrious)">Appearance (Anima and Illustrious)</h3><pre><code>orange hair, long hair, purple headband, red lips, purple eyes</code></pre><h3 id="default-outfit">Default Outfit</h3>Anima<pre><code>green scarf around neck, purple dress, pink pantyhose</code></pre>Illustrious<pre><code>green scarf, purple dress, pink pantyhose</code></pre>For full-body generations, you can add:<pre><code>purple footwear</code></pre>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 Daphne's identity.<h3 id="suggested-generation-settings">Suggested Generation Settings</h3>My testing was done using:ANIMA Settings with Turbo LoRA<ul><li>LoRA weight: 0.9</li><li>Sampler: Euler a</li><li>Scheduler: Simple</li><li>Steps: 12</li><li>CFG: 2.5</li></ul>Illustrious SettingsUse appropriate quality and negative tags mentioned in the WAI_11 documentation, or you can use positive and negative embeddings. I generated my images using Smooth Positive and Negative embeddings along with Face Detailer for final face refinement.<ul><li>LoRA weight: 0.8</li><li>Sampler: Euler a</li><li>Scheduler: Simple</li><li>Steps: 27</li><li>CFG: 4.5</li></ul>You can refer to my images for more examples. I have tried to tag the training images with accurate metadata and seeds.

Files with SHA256: 0501becf1b9f55f06fcf9cd11b9fdc0afc9e7c8cf644245246fce52c79c433dd