支持原作者谢谢喵！まがき的上色风格我非常喜欢，通过不断调试素材最终炼出了这个丹，我个人还算比较满意，这个lora出全身图的效果不如近身图好，因为原作者全身图也没多少，权重最高1，请按自己喜好向下调整。底模依旧推荐RDBT 0.39B，如果喜欢这个lora请评论区多多返图，你们的返图就是对我最大的支持！爱你们（づ￣3￣）づ╭❤～触发词：@magakii<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">采样器推荐: er_sde, Euler, Euler aTrigger word: @magakiisamplers:<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"> er_sde, Euler, Euler aSupport the original artist, thank you!I really love まがき’s coloring style. After constantly tweaking and refining the dataset, I finally managed to train this LoRA, and I’m pretty satisfied with how it turned out.This LoRA doesn’t perform quite as well for full-body images as it does for close-up shots, since the original artist doesn’t have that many full-body artworks. The maximum recommended weight is 1.0, so feel free to lower it according to your own preferences.I still recommend RDBT 0.39B as the base model.If you like this LoRA, please share your generations in the gallery! Your images are the biggest support for me! Love you guys!（づ￣3￣）づ╭❤～

Files with SHA256: d580bbed918df82f8f560cf8577aaf53c0c776a9b68d90c126fb296836bbad35