Experimental Model

raez.safetensors

v1.0

<h3>Short description</h3>
<p>A Pokémon-oriented style LoRA inspired by Azre, aimed at clean creature illustration, readable anatomy, and a stylized digital finish. It works best when the prompt already defines the creature clearly and the LoRA is used to shape the overall visual language.</p>
<h3>Generation parameters</h3>
<ul>
<li>Base model(s): Illustrious</li>
<li>Trigger(s): Illustrious v1.0: <code>azre</code></li>
<li>LoRA weight: <code>1.0</code> (recommended starting point; lower it mainly when stacking multiple LoRAs or when you want a softer style influence)</li>
<li>Sampler: <code>Euler a</code> for a looser creature/cartoon look, or <code>DPM++ 2M SDE Karras</code> for cleaner anatomy</li>
<li>Steps: <code>26–34</code></li>
<li>CFG: <code>4.5–6</code></li>
<li>Resolution: <code>1024×1024</code>, <code>832×1216</code>, or <code>1216×832</code></li>
<li>Describe species/form explicitly (<code>feral</code>, <code>anthro</code>, creature species, body type) so the LoRA shapes style without having to guess anatomy.</li>
</ul>
<h3>Prompt examples</h3>
<blockquote><p><strong>TODO:</strong> Add 2–3 prompt examples validated against the current version.</p></blockquote>
<h3>Give me a hand</h3>
<p>If you try Azre with clearly defined Pokémon or creature prompts, share the results so I can see how reliably the style follows different designs. Feedback about anatomy, readability, or prompt conflicts is particularly useful; if the LoRA works for you, an upvote is appreciated.</p>
<h3>Suggestions</h3>
<p>Recommended base from this profile: <strong>SweetIllustrious</strong>. For a controlled style blend, try <strong>Kajinchu | [Illustrious]</strong> at a low secondary weight (<code>0.2–0.45</code>) and keep this LoRA as the dominant style.</p>

Files with SHA256: fc37b5b72b8de137eac81d6d50b2a6d3ac3e55cdeb2a7c97f2aa3999964d074c