<h2 id="how-to-use">How to use</h2><p>It is recommended to write the following tokens: <strong>many different flowers, blurry background, nebulous bouquets, liquid smoke, RAW, high quality, floating in the smoke, foggy, purple flowers in a blue vase, red flowers.</strong></p><p>Copy the prompt and parameters <strong>from the preview</strong> to this model — you will not lose.</p><h2 id="what-the-model-is-suitable-for">What the model is suitable for</h2><p>The model trained on photographs of flowers placed in liquid nitrogen vapors. This gave the effect of haze and fog, which the model remembered well.</p><p><strong>LoRA </strong>was trained on a variety of examples, so try combinations and share your creativity in the comments.</p><p>I trained LoRA on the<strong> Deliberate_v3</strong> model, so it's better to work with her in pairs.</p><p>I recommend using <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">sd-dynamic-thresholding</a> extension to increase the stability of generation and improve quality.</p><p>The model was trained for a resolution of <strong>1024px</strong>, so you can generate huge images.</p><h2 id="which-model-works-best-with">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_v3</a> model, but you can combine this LoRA with other solutions focused on photorealism, model will work perfectly with them.</p><h2 id="links-to-my-resources">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>

Files with SHA256: 146912a11ffd98095f793b4cd2aa93cfa6fc73aa7829e0ef844f24d20b2c7c0b