——【元素法典】:Yuno779
我想得到更多的生成图来确认我的训练方法是否正确,如果可能请多在评论区发一下图片
I would like to get more generated graphs to confirm whether my training method is correct. Please send more pictures in the comment section if possible
群友的模型经过训练改良,原模型是IceFantasy V2.0
Trained and modified by the model of the group
大约在4090上训练了13小时,经历了两次返工重做
Trained for about 13 hours on 4090 and went through two reworks
IceFantasy Vre anything train
下图是原版模型和修复版模型的同参数对照图
Below is a comparison of the original model and the restored model with the same parameters
模型无需外挂VAE。
VAE does not need to be VAE externally applied to the model.
部分情况下可能出现过度拟合,如有此类情况请和我进行反馈
Overfitting may occur in some cases. Please give me feedback if there are such cases
请不要添加“masterpiece”等起手式,除非画面出现各种问题
Please do not add "masterpiece" or other prompt words
CFG可以推荐设置在3~30之间
CFG can be set between 3 and 30, AI painting has infinite possibilities
个人制作能力有限,模型并不会非常完美,并且可能与人们的期望不同
My crafting skills are limited, the model will not be perfect, and it may not be what people expect
可能不适合搭配使用例如badhand或者EasyNegative等
May not be suitable for use together such as badhand or EasyNegative etc
部分未经训练的部分可能依旧会出现无法准确反映tag的情况
Some parts not involved in training still cannot accurately reflect the tag information
请根据自己的情况使用高清修复,有的时候开启高清修复效果反而并不如直接出图
Hires. fix according to your own situation. Sometimes, opening Hires. fix results are not as straightforward as drawing
不建议继续进行训练
Do not recommend for Fine-tuning.
当然了,跟所有的模型都一样,这个说明放在这里只是为了叠甲,该怎么玩怎么玩就是了。
Of course, as with all models, this instruction is just there in case something goes wrong.
你可以随意将本模型融合到其他地方,但如果你共享该融合模型,别忘了标注一下:原模型:@yzxzc,模型修复:Yuno779
We allow you to merge with another model, but if you share that merge model, don't forget to add me to the credits.
除此之外允许任何人复制和修改模型,但是请遵守CreativeML Open RAIL-这里是M.CreativeML Open RAIL-M相关内容:
Anyone else is allowed to copy and modify the model, but please comply with CreativeML Open RAIL-M.You can learn more about the CreativeML Open RAIL-M here:
模型可以和其他模型一样随意使用,但是请遵守所在地区的法律法规,以免造成麻烦(我们并不负责)
The model can be used as freely as other models, but please abide by the local laws and regulations, so as not to cause trouble (we are not responsible for it).
@yzxzc:原本的模型
Automatic1111: SD-WebUI
Danbooru:打标器,帮助标准训练集
秋叶甜品店:这里的朋友委托我改良这个模型