<h1 id="krea-2-or-whyx-mature-x-turbo-fp8">🎨 Krea 2 | Whyx - Mature-X [Turbo] FP8</h1><h3 id="medium-tune-ver.">Medium-Tune ver.</h3><hr /><h2 id="about-the-model">📖 About the Model</h2>Base model: Krea 2 Turbo BF16 - Tuned into FP8 Precision: Semi-Precision FP8 - Scale. Model size: 12.5-13 GB Prompting: Natural Captions &amp; Booru TagsFP8 Scaled precision means full compatibility with LoRA. The model works best with them: styles, characters, and more.<ul><li>🎯 baked-in Mature Style. The model have mixed-in styles.</li><li>🖼️ Small Tune. The dataset was expanded with a tuned set of 2,000 high-quality images. It's a small-tune that barely affects overall quality.</li><li>🏷️ Flexible prompting. Works with both Captions and Booru Tags.</li><li>🔁 A good replacement for Illustrious or Anima models.</li></ul>This is the second release, so I run to some big experiments with the model.<hr /><h2 id="recommended-settings">⚙️ Recommended Settings</h2>My settings for Krea 2 Turbo<ul><li>CLIP Skip: None (or 1)</li><li>CFG Scale: 1 – 1.5 (max)</li><li>Sampler: Euler (custom preset)</li><li>Scheduler: SGM_Uniform, Beta, or Normal, Simple ⭐ best way!</li><li>Steps: 8 – 10 (max)</li><li>Hi-Res Fix: ❌ None</li><li>ADetailer: ❌ None</li></ul><hr />💬 Feedback and example images are very welcome. Please leave a review and share your results!

Files with SHA256: 8a24aa59fcf4b16af8418c394d765d64dec88338e629f728d52ac07e1e132ce5