Type | |
Stats | 479 |
Reviews | (89) |
Published | Sep 1, 2023 |
Base Model | |
Hash | AutoV2 E35BF8684F |
SDXL model trained with thickly coated images
使用厚涂风格图像训练的 SDXL 模型
It is recommended to use LORA into the model to create even more marvelous results.
推荐使用LORA 到模型中，来创造出更奇妙的结果。
Steps: 40
Sampler: DPM++ SDE Karras
Upscaler (Hires. fix): R-ESRGAN 4x+ Anime6B
Denoising strength: 0.5
Upscale by: 1.5+
CFG scale: 7-13
Recommended Prompt：highres,detailed,best quality,masterpiece,illustration,wallpaper
Recommended Negative prompt：(worst quality, low quality:1.4),nsfw,(hand with more than 5 fingers, hand with less than 4 fingers,ad anatomy, bad hands,mutated hands and fingers:1.2),extra legs,extra arms,interlocked fingers,duplicate,cropped,text,jpeg artifacts,signature,watermark,username,blurry,artist name,trademark,title,muscular,sd character,multiple view,Reference sheet,long body,malformed limbs,multiple breasts,cloned face,malformed,mutated,bad anatomy,disfigured,bad proportions,duplicate,bad feet,artist name,extra limbs,ugly,fused anus,text font ui,missing limb,
This merger is very easy to prompt, but better prompted engineering yields better results.
这种合并非常容易促成，但更好的提示会产生更好的效果。
Note Do not use negative embedding when there is no problem with the image.
注意 当图像没有问题时，请勿使用负嵌入。
Credit me if you use my model in your own merges
如果您在自己的合并中使用我的模型，请注明出处
if you would like to support me:https://www.buymeacoffee.com/EEEMax