为什么叫白糖糕呢？因为它扎实朴素、香甜醇厚~Eng description below. 更多例图下面相册请~为什么上面例图显示inpaint：我用了Tiled Diffusion, 也就是 Multidiffusion 插件来upscale，主要就是会让图片更好看，你可以用常规方式upscale，当然也可以用txt2img产图。原版未经MD：<a target="_blank" rel="ugc" href="https://civarchive.com/posts/136259">https://civarchive.com/posts/136259</a>Feel free to merge this lora into lora/models/anything else that I don't know (if only you aren't trying to make money from it of course). 如想与其他lora/模型等混合，只要不盈利——敬请随意。Reason why the sample images displayed as inpainting: I'm using the Tiled Diffusion, aka Multidiffusion plugin to upscale, you can of course generate with txt2img——myself did that, and sent the outcome to img2img, then upscaled it lel.Original txt2img generates <a target="_blank" rel="ugc" href="https://civarchive.com/posts/136259">https://civarchive.com/posts/136259</a>推荐CFG：如果没有Dynamic Thresholding就7，但是我强烈推荐Dynamic Thresholding插件，开20CFG，所有东西都好看一万倍（？推荐分辨率：啥·都·行·呀，图里你们也看见了啥分辨率都有，就没不行的（草推荐模型：我是在based64mix、holokukiv2.2上测试的，不过AOM3也不是不行，其他的自己试试也好啦。Recommended CFG: 7 without Dynamic Thresholding Plugin, 14-20 with Dynamic Thresholding.Recommended resolution: literally anything has been successful on my end, you can see it in the preview pics lel.Recommended model: I've tested on based64mix、holokukiv2.2, however, AOM3、somethingv2_2 could also produce some nice things, feel free to test on other models!

Files with SHA256: d2b21f405b648aedd4e7d729b8171e3aa9f54462b7f23f4545462aff1f4e98a7