<h2>How to use</h2><p>To use it, you need to register <strong>&lt;lora:disoptics_yiu_v12:0.85&gt;</strong> in the prompt field. I recommend exactly this value of the LoRA weight, as it gives more variability.</p><p>It is recommended to write the following tokens: <strong><em>design, glass lines, CIFilters, distortion, refraction, simple composition</em></strong>.</p><p>Copy the prompta and parameters <strong>from the preview</strong> to this model — you will not lose.</p><h2>What the model is suitable for</h2><p>This model is needed to simulate forced displacement and refraction of light. She copes well with the tokens "man, "woman" and abstract objects.</p><p>I trained LoRA on the<strong> Deliberate_v2</strong> model, so it's better to work with her in pairs.</p><h2>Which model works best with</h2><p>It is best to use the <a target="_blank" rel="ugc" href="https://civarchive.com/models/4823/deliberate">Deliberate_v2</a> model.</p><h2>Links to my resources</h2><p>You will find help in my telegram <a target="_blank" rel="ugc" href="https://t.me/yiu_chat">chat</a>.<br />My Telegram <a target="_blank" rel="ugc" href="https://t.me/neuro_yiu">channel</a>.</p>

Disoptics

<p>Better elaboration of the face and texture of the glass</p>

Files with SHA256: 817d8a0da216d28d79433cf88a9dd892215f533af6e73563398f069745c2ab71