<h1 id="sdxl-flash-fyl4mtffx">SDXL Flash</h1><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3ee838c1-52ab-4201-a6d1-94a6680258fa/width=525/3ee838c1-52ab-4201-a6d1-94a6680258fa.jpeg" />Introducing the new fast model SDXL Flash, we learned that all fast XL models work fast, but the quality decreases, and we also made a fast model, but it is not as fast as LCM, Turbo, Lightning and Hyper, but the quality is higher. Below you will see the study with steps and cfg.<h3 id="steps-and-cfg-(guidance)-prxk6two4">Steps and CFG (Guidance)</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8b9d1bb3-7ef4-43cd-9b63-1b0abae380f7/width=525/8b9d1bb3-7ef4-43cd-9b63-1b0abae380f7.jpeg" /><h3 id="optimal-settings-rqj2s5d4o">Optimal settings</h3><ul><li>Steps: 6-9</li><li>CFG Scale: 2.5-3.5</li><li>Sampler: DPM++ SDE</li></ul>

SDXL Flash

--&gt; Work with LoRA &lt;--<ul><li>Trigger word: &lt;lora:sdxlFlash_lora:0.55&gt;</li><li>Optimal LoRA multiplier: 0.45-0.6 (the best - 0.55)</li><li>Optimal base model: <a target="_blank" rel="ugc" href="https://civitai.com/models/324891?modelVersionId=479685">FluentlyXL v4</a></li></ul>

Files with SHA256: f12b364076e5f35899eeef3220d96fc135c164d99b15151031c99054b6bb51a5