<h3 id="zombie-style-lora-for-anima-3.8b">Zombie Style LoRA for Anima 3.8B</h3>Ported one of my favorite NoobAI styles over to Anima 3.8B. From <a target="_blank" rel="ugc" href="https://civarchive.com/models/1627574/zombie-style?modelVersionId=1842113">Zombie-Style</a><hr />Note: Trained on Delta Mix Anima (3.8B). I have not tested it on other Anima 3.8B models, so results on different checkpoints or base versions are not guaranteed.<hr /><h3 id="usage-and-recommended-settings">Usage &amp; Recommended Settings</h3>Base Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2896329/anima-delta-mix-38b-qwen-06b?modelVersionId=3405806">Anima Delta Mix 3.8B</a>Trigger Word: <code>@zombie_style</code>LoRA Strength: <code>0.85 - 1.3</code> (<code>1.1</code> is the sweet spot)Sampler: <code>euler_ancestral</code>Scheduler: <code>simple</code>Dual-Pass CFG<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">: Pass 1: <code>4.6</code><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px"> (11 steps) | Pass 2: <code>3.6</code><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px"> (15 steps, denoise <code>0.5</code><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">)<hr />Prompt structure@zombie_style, safe, masterpiece, 1girl, solo...<hr /><h3 id="training-details">Training Details</h3>Dataset: 53 hand-picked and curated high-resolution images.Architecture: Anima 3.8B Cosmos DiT LoRA (Rank 32, Alpha 128).Epochs: 10 epochs (530 steps), AdamW fused.<hr />Drop a review or showcase below if you like it, and let me know in the comments what artist or character you want me to train on Anima next!

Files with SHA256: d83b1b0d352ec703df9e8d176d02baa354b07942825e6b9b9aec21e1ea6771aa