signalviolet_style — Anima LoRA (Style)<code>signalviolet_style</code> is a style LoRA fine-tuned from the artwork of the illustrator signalviolet, capturing their characteristic soft, delicate anime aesthetic — clean cel shading, gentle blush, and cute, expressive heroines with a slightly glossy finish.Training details<ul><li>Base model: Anima Base V1.0 (circlestone-labs)</li><li>Dataset: 327 curated illustrations (danbooru/Gelbooru style tags)</li><li>Network: LoRA, rank 32 / alpha 16</li><li>Epochs: 10 (~820 steps), AdamW 8-bit</li><li>Architecture: anima-preview/lora (SDXL-based, epsilon prediction)</li></ul>Trigger wordPlain Text<pre><code>signalviolet</code></pre>Place it at the beginning of your prompt (kept token).Recommended settingsParameterValueBase modelAnima Base V1.0Text encoderqwen_3_06b_baseVAEqwen_image_vaeLoRA weight0.6 – 0.8 (start at 0.7; lower for complex compositions)Sampler / Schedulerer_sde / simple (or euler_a, dpmpp_2m_sde)Steps30 – 50CFG4 – 5Resolution512² – 1536² px (e.g. 832×1216, 1024×1024)Recommended positive<code>masterpiece, best quality, score_7, safe, signalviolet, ...</code>Recommended negative<code>worst quality, low quality, score_1, score_2, score_3, artist name, blurry, jpeg artifacts, chromatic aberration</code>

signalviolet_style

<code>Initial release. Trained on 327 images with Anima Base V1.0.</code>

Files with SHA256: 59bdabaf34fa9faff411be2b8e7595fc073e63a6e50e044e296be2258196c7dd