<h2 id="recommended-settings">⚙️ Recommended Settings</h2><h3 id="anima">🐰 Anima</h3><ul><li>LoRA weight: <code>0.8</code></li><li>Steps: <code>40</code></li><li>CFG Scale: <code>3.0</code></li><li>Sampler: <code>er_sde/normal</code></li><li>Scheduler: <code>Beta</code></li></ul><hr /><h3 id="illustrious">✨ Illustrious</h3>Tested with: <code>CyberIllustrious Semi</code> and <code>WAI</code><ul><li>LoRA weight: <code>0.8</code></li><li>Steps: <code>40</code></li><li>CFG Scale: <code>3.0–4.0</code></li><li>Sampler: <code>DPM++ 3M SDE GPU</code></li><li>Scheduler: <code>Karras</code></li></ul><hr /><h3 id="pony">🐴 Pony</h3>Recommended settings for the best results:<ul><li>Samplers: <code>DPM 2</code> or <code>DPM++ 2M</code></li><li>Scheduler: <code>Karras</code></li><li>Steps: <code>20–40</code></li><li>CFG Scale: <code>4–6</code></li></ul><hr /><h3 id="sd-3.5">💠 SD 3.5</h3>This version was trained on <code>SD 3.5 Large</code>. It has not been tested with other SD 3.5 checkpoints.Recommended settings for the best results:<ul><li>Steps: <code>20–40</code></li><li>CFG Scale: <code>4–7</code></li><li>Scheduler: <code>SGM Uniform</code></li></ul><hr /><h3 id="flux.1">🔥 FLUX.1</h3>This version was trained on <code>FLUX.1 Dev</code>, but it also works well with <code>FLUX.1 Schnell</code>.The training dataset includes official character images and my own SDXL generations. I plan to continue improving the model in future updates to achieve more consistent and accurate results.Recommended settings:<ul><li>Sampler: <code>Euler</code></li><li>Scheduler: <code>Simple</code></li><li>Steps: <code>20</code></li></ul><hr />These settings are recommended as a starting point. Results may vary depending on the checkpoint, prompt, seed, resolution, and LoRA weight.

LadyBug

anilad.safetensors

Ladybug (Anima)

Files with SHA256: 19ef1c824b02d37294d332fdc24fca0b4d2458232af8721dcd70fa1a989dd118