青禾SDXL-anime-Pony版本beta (ID: 474626)

青禾SDXL-Pony

模型选用 pony V6当做底膜，重新挑选了一些相似风格画师的图片去训练的,此版本继承了Ponydiffusion的起手式出图方式，由于训练的问题，现在模型主要是以画人为主，对于除人物以外的动物，风景，以及多概念已经不是很支持了，模型已经内置了VAE，所以VAE选择Automatic 或者 none,

•Model selection pony V6 as the bottom film, re-select some similar style painter pictures to train, this version inherits the Ponydiffusion hand-out method, due to the training problem, now the model is mainly to draw people, for animals, scenery, and multi-concept is not very support, the model has built VAE, Therefore, VAE is selected as Automatic or none.

---

【Recommended parameter】：

必要的起手式前置（Hint words for starting）：

score_9,score_8_up,score_7_up,score_6_up,masterpiece,best quality,ultra-detailed,very aesthetic,absurdres,

负面（Negative prompt）：

score_6,score_5,score_4,(worst quality:1.2),(low quality:1.2),bad hands,missing fingers,three legs,wrong hand,wrong feet,wrong fingers,deformed leg,abnormal,malformation,(bad neck:1.2),(long neck:1.5),

采样方法（sampler）：Euler a    

迭代步数（steps）：30      

CFG Scale：8      

分辨率不建议低于1024，设备允许情况下,可以开个高清修复,

• Resolution is not recommended below 1024, if the device allows, you can open a high-definition repair,

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

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.

描述:

【推荐参数】：

必要的起手式前置（For higher quality outcomes, prepend prompts with）：

score_9,score_8_up,score_7_up,score_6_up,masterpiece,best quality,ultra-detailed,very aesthetic,absurdres,

负面（Negative）：

score_6,score_5,score_4,(worst quality:1.2),(low quality:1.2),bad hands,missing fingers,three legs,wrong hand,wrong feet,wrong fingers,deformed leg,abnormal,malformation,(bad neck:1.2),(long neck:1.5),

采样方法（Sampler）：Euler a    这个采样器，在切换提示词，往往第一张会画不好，第二张才会正常点

迭代步数（Steps）：30      

CFG：8      

分辨率不建议低于1024，设备允许情况下,可以开个高清修复,

• Resolution is not recommended below 1024, if the device allows, you can open a high-definition repair,

祝大家玩的开心，有练得不好的地方多包涵   ღ( ´･ᴗ･` )

Have fun, everybody！

训练词语: