<h3 id="v2-v2a-v2b-kzh0nxma8">v2 / v2A / v2B</h3><p>The prompt requires a trigger word.</p><p>This is a v-prediction model. it must be used in a v-prediction support program.</p><p></p><h3 id="v1-2e2dqk3vd">v1</h3><p>recommend CFG - 1.5~2</p><p>This checkpoint is merged with DPO LoRA.</p><p>Recommended <span style="color:rgb(193, 194, 197)">Prompt -</span> hdr 8k analog photo,</p><p><span style="color:rgb(193, 194, 197)">Recommended Negative Prompt : </span>big eyes, jpeg artifacts, (airbrushed, cartoon, anime, manga:1.4), (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4)</p>

Files with SHA256: 0154507fe07cf8ed18ee4c715b7eb30b09b282c96edbe2a4fe22f87ebe36d85c