MiaoMiao 3D Harem版本PDXL-Beta1.1 (ID: 497764)

This model is similar to a 3D rendering modeling style. Due to the difficulty in finding model materials in this field, the current model version has been updated to NBXL1.0, and the model still needs improvement in the future

The recommended weight for using this model with the LORA model is between 0.6 and 0.8

———————————————————————————————————————

—————————

Suggest drawing parameters

sampler:



Euler a: 30 steps



hires.fix:  4x-ultrasharp 



cfg scale: 7.0  



Resolution of portrait characters： 768x1280 ，1024x1024



clip skip: 2



Local map generation can be enabled：ADetailer

1.Hint words for starting：

,masterpiece,best quality,very aesthetic,highres,absurdres,sensitive,photo background,shiny_skin,wet skin,3D, unreal, unity, blender,smooth skin,

Negative prompt：

lowres,(bad),text,error,bad feet,fewer,extra,missing,worst quality,jpeg artifacts,low quality,watermark,unfinished,displeasing,oldest,early,chromatic aberration,signature,artistic error,username,scan,[abstract],english text,

Model Usage Statement

1. You are not allowed to host this model and its derivative versions (such as fusion model versions) on websites/applications that plan to earn income or donate. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, using images for public publication on short video platforms, etc.), please contact me through the website

2. You are not allowed to directly sell images generated by this model, unless you have made sufficient manual modifications to the image so that it can be fully recognized as your personal work in a legal sense. If you violate this provision, all legal consequences resulting from it shall be borne by you personally, and I am not responsible.

3. You cannot use this model to intentionally create or share illegal or harmful content for dissemination and output. Please abide by public order and morality, and use this model for positive purposes.

This model does not contain any real-life material, image sources, or training codes from the internet. The model is only used for scientific research interest exchange

描述:

Hint words for starting：

score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_up,

Negative prompt：

source_anime,score_6,score_5,score_4,ugly face,mutated hands,blurry face,bad hands,cleavage,nipples,text,watermark,

推荐出图画布大小（Recommended canvas size for drawing）

1024 x 1024	1：1 



1152 x 896	9:7



896 x 1152	7:9



1216 x 832	19:13



832 x 1216	13:19



1344 x 768	7：4 



768 x 1344	4：7 



1536 x 640	12：5 



640 x 1536	5：12

推荐出图参数（Recommended drawing parameters）

采样方法（sampler）:



Euler a: 30步



高清修复（hires.fix）: R-ESRGAN 4x+ Anime6B  , 



高分迭代步数 10 重绘幅度 0.3



提示词引导系数 (cfg scale): 6 



clip skip: 2

sampler:



Euler a: 30 steps



hires.fix:  R-ESRGAN 4x+ Anime6B



High score iteration steps 10



Redraw amplitude 0.3



cfg scale: 6.0  



Resolution of portrait characters： 768x1280 ，1024x1024



clip skip: 2



Local map generation can be enabled：ADetailer

训练词语: