Attempt to recreate MadDogAi artstyle.Recommended Settings:<ul><li>Strength: 0.8-1.3</li><li>CFG: 4-5 (Non-Turbo recommended for best results)</li><li>Steps: 24-30</li><li>Upscaling: Recommended (Denoise 0.20-0.40)</li></ul>Version Notes:<ul><li>Illustrious: Tends to add black lipstick due to the training set. May want to add lip color to prevent this. Trained on old images.</li><li>Anima (v1): Fixed illustrious errors, trained on recent dataset.</li><li>Anima (v2): Trained on newer images. Refined training settings and prompting for training. Works better than v1 on Anima Base 1, removing some of the "squished" feeling it had.</li></ul><ul><li>Important Style Notes:</li></ul><ul><li>Material Rendering: Black clothing will naturally render with a glossy, latex-like texture.</li><li>Physique: The LoRA is heavily biased toward muscular, thick-thighed female characters. </li><li>Lighting: This LoRA responds strongly to lighting prompts. If you want flat, bright lighting, you must explicitly prompt for it (e.g., <code>flat lighting, very bright, daylight</code>).</li></ul>Negative Prompt Suggestions:<ul><li>To force pale skin: <code>warm lighting, orange tint, red shadows, tan skin:1.2</code></li><li>To prevent melted hands/limbs: <code>bad anatomy, melted fingers, limb bleed</code></li><li>To reduce latex look on non-black clothes: <code>latex, shiny fabric, glossy,</code></li><li>A lot of the images had sharp teeth, but it can generate normal teeth easily as long as <code>sharp teeth</code> isn't positively prompted. However, it is better to add <code>sharp teeth</code> in the negatives during upscaling since it can add them at that point.</li></ul>

MadDogAi

Attempt to recreate MadDogAi artstyle.Recommended Settings:<ul><li>Strength: 0.8-1.3</li><li>CFG: 4-5 (Non-Turbo recommended for best results)</li><li>Steps: 24-30</li><li>Upscaling: Recommended (Denoise 0.20-0.40)</li></ul>Version Notes:<ul><li>Illustrious: Tends to add black lipstick due to the training set. May want to add lip color to prevent this. Trained on old images.</li><li>Anima (v1): Fixed illustrious errors, trained on recent dataset.</li><li>Anima (v2): Newer on newer images. Refined training settings and prompting for training. Works better than v1 on Anima Base 1, removing some of the "squished" feeling it had.</li></ul><ul><li>Important Style Notes:</li></ul><ul><li>Material Rendering: Black clothing will naturally render with a glossy, latex-like texture.</li><li>Physique: The LoRA is heavily biased toward muscular, thick-thighed female characters.</li><li>Lighting: This LoRA responds strongly to lighting prompts. If you want flat, bright lighting, you must explicitly prompt for it (e.g., <code>flat lighting, very bright, daylight</code>).</li></ul>Negative Prompt Suggestions:<ul><li>To force pale skin: <code>warm lighting, orange tint, red shadows, tan skin:1.2</code></li><li>To prevent melted hands/limbs: <code>bad anatomy, melted fingers, limb bleed</code></li><li>To reduce latex look on non-black clothes: <code>latex, shiny fabric, glossy,</code></li></ul>

Files with SHA256: 8c110b681b2046b2296e4e574ade724989ca8634613d7b8f4eb0b87b719cb47b