<h1 id="astx-moss">ASTX-MOSS</h1><hr /><h2 id="about-this-model">🎨 About this Model</h2>A fully merged-tuned model. All aspects of the model have been improved: better prompt comprehension, image quality, attention to detail. The model has been tested with standard parameters.The model creates images in various styles, from realism and 3D to pixel art; anime is optimized. The model is the best replacement option for Anima.<ul><li>🧬 Base: created on a MOSS-Base model merge, not SFT</li><li>🔞 Can produce NSFW content</li><li>⚡ A quantized version will be uploaded, but a bit later</li></ul><hr /><h2 id="settings">⚙️ Settings</h2>🎬 My settings for MOSS<ul><li>📸 CLIP Skip: 1 or None</li><li>🎲 CFG Scale: 3 – 3.5</li><li>🧼 Sampler / Scheduler: Res_Multistep or Euler with SGM_Uniform or Simple ⭐ best way!</li><li>👣 Steps: 25 – 35</li><li>♨️ Hi-Res Fix: ❌ I am not using it</li><li>🎭 ADetailer: ❌ I am not using it</li></ul><h3 id="recommended-resolution">📐 Recommended Resolution</h3><ul><li>1024×1536 / 1536×1024</li><li>832×1216 / 1216×832</li><li>Simple: 1024×1024</li></ul><hr /><h2 id="prompt-parameters">✨ Prompt Parameters</h2>✔️ Quality (MOSS): Natural Language and Booru Tags — no need for quality tags here.❌ Negative (MOSS):<pre><code>NONE</code></pre>

ASTX-MOSS

INT8 Convrot Quantization of ASTX-MOSS

Files with SHA256: 2a1d0e20da3a26779ef42ccf17cfe5a238ce8f0042396c7db2e5a8f515e800bd