Manga Rendering Style LoRA (Non-Identity)This LoRA is a manga artist–focused rendering style LoRA, trained to emphasize how things are drawn, not who is drawn.To avoid identity locking and average-face artifacts, the training data is intentionally distributed across many characters and complex compositions.Training overviewCharacters: 43 female / 28 maleImages per character: ~5–10Additional ~100 images with low identity emphasis(dynamic poses, complex layouts, manga panels, expressive linework)TaggingIdentity-focused tags were intentionally removedCaptions prioritize line quality, rendering state, and compositionUsageRecommended weight: 0.8 – 1.2Lower values → earlier / rougher styleHigher values → later / cleaner style⚠️ This LoRA is not intended for reproducing specific characters.Best used for style-driven manga rendering with flexible identity.
