Make sure to use UI that supports v-prediction, otherwise you will get a noisy blob!<h3 id="main-parameters:">Main parameters:</h3><ul><li>Steps: 28</li><li>CFG: 3-5</li><li>Sampler-scheduler: euler/euler a-normal, DDPM-exponential (better noses)</li><li>CFGZeroStar and sometimes Self-Attention Guidance: default for difficult backgrounds</li></ul>Try to BREAK prompts into parts by 75 tokens max, this goes for most models..<h3 id="positive-prompt:">Positive prompt:</h3><pre><code>number of characters (1girl/1boy), character name, artist prompt, scene/environment/camera angle, action, expression, items, quality prompts (masterpiece, best quality)</code></pre><ul><li>some heavily stylized characters might require prompt: nose, realistic.. you can put nose into Adetailer</li></ul><h3 id="negative-prompt:">Negative prompt:</h3><pre><code>lowres, worst quality</code></pre><ul><li>even longer negative should work, but I prefer simplicity.. tags worth noting include sketch, abstract, url</li></ul>Enjoy..

Grim Noire vPred

Found better settings for LoRA training for my use case, better translucent bodies. Added <a target="_blank" rel="ugc" href="https://civitai.com/models/510261?modelVersionId=567119">SPO-SDXL_4k-p_10ep_LoRA_webui</a> at low weight to bounce a bit of detail.

Files with SHA256: d19cb3a90b22009bbde067818007232f59daa186c9264a14188cdf93fc5c8b0a