Training objectives for SilvermoonMix-Evolved-Chenkin-Rectified-Flow:<ul><li>Stable hands</li><li>Optimized background and compositional logic for accurate lighting and multi-character generation</li><li>A neutral base style to ensure artist tags work effectively</li></ul>For instructions on how to use the RF model, please refer to <a target="_blank" rel="ugc" href="https://civarchive.com/models/2363696/chenkinnoob-xl-v02-rectified-flow">https://civarchive.com/models/2363696/chenkinnoob-xl-v02-rectified-flow</a>I mainly use <a target="_blank" rel="ugc" href="https://github.com/Panchovix/stable-diffusion-webui-reForge">ReForge</a>. Support for RF in ReForge is being implemented through a built-in extension:<a target="_blank" rel="ugc" href="https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/LpMF0lmC96X001Au9fFU_.png"><img src="https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/LpMF0lmC96X001Au9fFU_.png" alt="изображение" /></a><h3 id="why-rf">Why RF?</h3><ul><li>ChenkinNoob (both the original and RF versions) features an updated new knowledge base (up to 01/2026). However, the original ChenkinNoob was based on E-pred, which doesn't perform well on dark contents and has an issue where it tends to fill the entire picture—a stylistic trait I wanted to avoid.</li><li>The Rectified-Flow (RF) version resolves both of these issues.</li><li>The fine-tune result on the ChenkinNoob RF demonstrates good scene and limb logic. The raw generated results are already acceptable without using Hires. fix or ADetailer,</li><li>Artist tags perform closer to the artist's true style compared to the Noob-Vpred version. You can expect an approximate 20%-25% improvement in style accuracy.</li></ul><h3 id="recommended-settings:">Recommended settings:</h3><ul><li>Sampler: Euler A Comfy RF (for ReForge)/Euler</li><li>Steps: 20-28</li><li>CFG: around 5</li><li>Shift: around 3</li><li>Schedule: Normal / Simple / SGM Uniform / Beta</li><li>Positive Quality Tags: <code>masterpiece, best quality, aesthetic</code></li><li>Negative Tags: <code>worst quality, normal quality, bad anatomy, low resolution</code></li></ul>Note: All my demo images were generated via stable-diffusion-webui-reForge. You can right-click any of the demo images -&gt; open in a new tab to download the original image. You can then pull it into the webui's PNG info tab to see my exact generation settings.<hr />SilvermoonMix-Evolved-Chenkin-Rectified-Flow 的训练目标：<ul><li>稳定的手部生成</li><li>优化背景与构图逻辑，以实现正确的光影表现和多人构图</li><li>保持中性的基础画风，确保画师标签（Artist tags）能良好生效</li></ul>有关如何使用 RF 模型的说明，请参考： <a target="_blank" rel="ugc" href="https://civarchive.com/models/2363696/chenkinnoob-xl-v02-rectified-flow">https://civarchive.com/models/2363696/chenkinnoob-xl-v02-rectified-flow</a>我主要使用 <a target="_blank" rel="ugc" href="https://github.com/Panchovix/stable-diffusion-webui-reForge">ReForge</a>。ReForge 对 RF 的支持正通过一个内置扩展来实现：<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6eea9f53-76b0-4295-96ac-46a518921b19/original=true/6eea9f53-76b0-4295-96ac-46a518921b19.jpeg" /><h3 id="rf">为什么选择 RF 版本？</h3><ul><li>ChenkinNoob（原版和 RF 版）都拥有最新的知识库（截至 2026 年 1 月）。但是，原版 ChenkinNoob 是基于 E-pred 的，它在处理暗部内容时表现不佳，并且倾向于把整个画面填满，我不喜欢这种风格。</li><li>RF 版本完美解决了这两个问题。</li><li>此外，在ChenkinNoob RF 上的微调结果展现出了非常优秀的场景和肢体逻辑。即使不使用 Hires. fix（高清修复）和 ADetailer，直接生成的原图效果也已经非常不错且完全可以接受了。</li><li>画师 tag 的表现更加贴近原画师的真实风格。与 Noob-Vpred 版本相比，画风的还原度大约提升了 20%-25%。</li></ul><h3>推荐设置：</h3><ul><li>采样方法 (Sampler): Euler A Comfy RF (ReForge自带)/Euler</li><li>迭代步数 (Steps): 20-28</li><li>提示词引导系数 (CFG): 5 左右</li><li>Shift: 3 左右</li><li>调度器 (Schedule): Normal / Simple / SGM Uniform / Beta</li><li>正面质量提示词: <code>masterpiece, best quality, aesthetic</code></li><li>负面提示词: <code>worst quality, normal quality, bad anatomy, low resolution</code></li></ul>注意： 我所有的示例图片都是使用 stable-diffusion-webui-reForge 生成的。您可以右键单击任何示例图片 -&gt; 在新标签页中打开以保存原图。然后，您可以将其拖入 WebUI 的 PNG Info 选项卡中来查看我的具体生成参数。Change notes:<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">v2.0: Fine-tuned on ChenkinNoob-XL-v0.3 Rectified-Flow<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">.

SilvermoonMix-Evolved-Chenkin-Rectified-Flow

v2.0: Fine-tuned on ChenkinNoob-XL-v0.3 Rectified-Flow.

Files with SHA256: 8b23530bd184b23524d0c873fa5dadcc90c510cf4a613d3061d64d280f4de039