<h2 id="introduction">Introduction</h2><p>This model is fine-tuned from <a target="_blank" rel="ugc" href="https://civarchive.com/models/2458426/anima"><strong>Anima Base 1.0</strong></a>.<br />It focuses on cute and diverse anime-style outputs while improving overall stability.</p><h2 id="recommended-settings">Recommended Settings</h2><p><strong>Steps:</strong> 20–30<br /><strong>CFG scale:</strong> 4–5<br /><strong>Sampler:</strong> ER SDE / Euler A</p><h2 id="notes">Notes</h2><p>If you encounter any issues, please leave feedback so I can try to improve them in future versions.</p><p></p><p></p>

Q-ANIMA

<p>For v2, DPO training was conducted on approximately 3,000 preference pairs to improve model quality.</p>

Files with SHA256: aea2726a1261d156f4bb80d72e85a555f7dd61a7e7e13bd197605e901129344a