欢迎使用，，lora名字自己改一下，我重新改了下名tag识别不出，请下载原图到sd反推底模是： <a target="_blank" rel="ugc" href="https://huggingface.co/jmts0925/model_breakDomain/tree/main">breakdomain_M2150</a>   ，<a target="_blank" rel="ugc" href="https://ko-fi.com/s/9dd78df21d">dalcefoPainting_3rd，</a>anything，embeddings模型：     EasyNegative，ng_deepnegative_v1_75t，badhandv4   需要下载，，不然可能达不到效果VAE:                             vae-ft-mse-840000，万能vae，，，其它vae也可以试试。色彩会有点点不一样Sampler:                     DPM++ SDE Karras,    Euler a，DPM++ 2M Karras，每种都有一点点不同的效果。自己测试CFG scale:                   7-9采样：                         20-40人物占比很小。应该都是烂脸的。可以打no humans，加高权重不出人，或者开超大分辨率看看脸能不能好。不然就用插件或者其它方法修，我一般用的是512x768，高清修复放大2倍1024x1536,或更大，不要同时用脸部修复，横图是768x512,————————————————————————————————————————————————————————————————————————————————Welcome to use, change the name "lora" to your own name, I have renamed it.If the tag cannot be recognized, please download the original image to the SD card for reverse pushing.The base model is: <a rel="ugc" href="https://huggingface.co/jmts0925/model_breakDomain/tree/main">breakdomain_M2150</a>, <a rel="ugc" href="https://ko-fi.com/s/9dd78df21d">dalcefoPainting_3rd</a>, anything.Embeddings models: EasyNegative, ng_deepnegative_v1_75t, badhandv4. They need to be downloaded, otherwise the effect may not be achieved.VAE: vae-ft-mse-840000, universal vae, other vae can also be tried. The colors may be slightly different.Sampler: DPM++ SDE Karras, Euler a, DPM++ 2M Karras. Each has a slightly different effect. Please test it yourself.CFG scale: 7-9Sampling: 20-40The proportion of people is very small. They should all have bad faces. You can use "no humans" and increase the weight to exclude people, or try to view the face with a very high resolution. Otherwise, you can use plugins or other methods to repair them. I usually use 512x768, and high-definition restoration can be enlarged by 2 times to 1024x1536 or larger, but do not use facial repair at the same time. The horizontal image is 768x512.

Animation landscape/动漫风景

fengjing.safetensors

v1.0

anime scene

Welcome to use it, I changed Lora's name myself, I changed my next name The tag is not recognized, please download the original image to SD and reverse, or>> <a href="https://civitai.com/models/103811/animation-landscape" target="_blank"> Station C has the same name</a> , and the bottom model with complete tag information is: > ; > <a href="https://huggingface.co/jmts0925/model_breakDomain/tree/main" target="_blank">breakDomain_M2150</a>, >> <a href="https://ko-fi.com/s/9dd78df21d" target="_blank">DalcePopainting_3rd,</a> anything, embeddings model: easyNegative, ng_deepnegative_v1_75t, badhandv4 need to be downloaded, otherwise it may not work VAE: & nbsp; vae-ft-mse-840000, universal vae,,, you can also try other vae. The color will be slightly different Sampler: DPM++ SDE Karras, Euler a, DPM++ 2M Karras, each has a slightly different effect. Test yourself CFG scale: 7-9 samples: & nbsp; 20-40 The proportion of characters is very small. They must all be disgusting. You can hit No Humans, increase the weight so it doesn't stand out, or turn on super high resolution to see if your face looks good. Otherwise, use plug-ins or other methods to fix it. I usually use 512x768, high-definition restoration, double magnification 1024x1536, or larger. Don't use facial restoration at the same time. The horizontal image is 768x512.

Files with SHA256: e2f1a9a1119c326ffbc14bcba320f9ebf6ec7428c78a12e67cd6c64883635a71