mix of many models, VAE is baked,good at NSFW
很多模型的混合,vae已经烘焙,擅长nsfw
setting:
Denoising strength: 0.55,
Clip skip: 2,
ENSD: 31337,
Hires upscale: 4,
Hires steps: 15,
Hires upscaler: R-ESRGAN 4x+,
Eta: 0.68
2023.3.19 update
添加了两个版本,0.8a更真实,0.8c更动漫画
Two additional versions were added, 0.8a being more realistic and 0.8c being more anime
2023.6.13 update
更新测试版本0.9,此版本非常不稳定,很考验玩家的负面关键词使用熟练度,达到示例图效果需要下载所需lora,必备面部修复插件和动态阈值插件,此版本不再烘焙VAE,但我个人建议还是使用vae-ft-mse-840000-ema-pruned,示例图全部由此VAE生成,经测试此版本容易出现手脚崩坏和服装单一问题,建议使用相关lora配合使用,所有示例图片可以直接拖入SD图像浏览器查看相关参数
Update test version 0.9, this version is very unstable, it is a test of the player's proficiency in using negative keywords, to achieve the effect of the example image, you need to download the required lora, necessary face repair plug-ins and dynamic threshold plug-ins, this version no longer bakes VAE, but Personally, I recommend using vae-ft-mse-840000-ema-pruned. All the example pictures are generated by this VAE. After testing, this version is prone to hand and foot collapse and clothing oversimulation. It is recommended to use related lora to cooperate with it. All picture parameters Can be directly dragged into the SD image browser to view related parameters
关于图像模糊问题
请使用controlnet进行分块放大修复,如果这还帮不到你你可以借助外援继续放大,电脑不太好的玩家建议使用Topaz和Upscayl进行放大,Upscayl目前是免费的而且速度很快,相关使用教程可以在YOUTUBE和BILIBILI上找到,有很多的视频博主讲解了contronlnet的使用方法,另外图像设置也尽量按照示例图参数不要随意改动,图像采样一般只用DPM++SDE,超级分辨率放大算法请使用4x-UltraSharp,当然其它的算法也可以自行尝试
About image blur
Please use controlnet to zoom in and repair the blocks. If this still doesn’t help you, you can continue to zoom in with the aid of foreign aid. Players with poor computers are recommended to use Topaz and Upscayl for zooming in. Upscayl is currently free and very fast. Related tutorials It can be found on YOUTUBE and BILIBILI. There are many video bloggers explaining how to use contronlnet. In addition, the image settings should also follow the example image parameters as much as possible and do not change at will. Generally, only DPM++SDE is used for image sampling. Super resolution zoom-in algorithm please Use 4x-UltraSharp, of course other algorithms can also be tried by yourself
写了这么长简介还不看,在评论区问的一律拖出去斩首
If you don’t read such a long introduction, anyone who asks in the comment area will be dragged out and beheaded
Description
FAQ
Comments (72)
0.9Beta look so great!! will you upload a SafeTensor version too ?
You can convert yourself, civitai upload is very slow now, that's why I don't update
Pretty sure beheading is illegal
It's a joke. I'm not gonna pick them up over the wire
Just wanted to be sure because I'm not familiar with your local laws
作者大大您好,我特别想复刻您的示例图,但是得到的结果差别很大,我注意到您用了很多负面embedding,我都下载下来了,和您的原图仍然有很大区别
看简介,看简介 ,看简介!
想要复刻我的示例图首先你需要把图片下载下来拖入sd的图片浏览器查看参数,你c的参数根本就是不完整的,sd里会读取图片的所有完整参数,其次如果你非要按照示例图片跑以下条件缺一不可:
1.动态阈值插件(必须)
2.高分辨率修复(必须)
3.图像参数里的lora(必须)
4.图片采样参数(必须)
负面嵌入其实没那么重要,你只需要把常用的几个下载下来就行,另外有的图片我是用了重绘和面部修复插件的,你当然不可能百分百还原
@zhazhahui345 请问一下作者大大的面部修复插件是什么呀
好开心还能看到继续更新,色彩风格跟以前不一样了,感觉以前的好看点,现在有点油腻
油腻的师姐在哪里
无敌
这是我用过的最好的模型之一,感谢作者继续更新。
感谢大佬更新!谢谢大佬!
大大可以加一些男生的数据吗 很喜欢这个模型的风格!谢谢谢谢~
You're truly king of prompts and models, especially the prompts. With your prompt I could obtain immensely good results from any model.
How did you come up with them, do you have any tips?
There is no good suggestion, but after running a lot of pictures, you can always sum up a general rule. This is a kind of experience. If you don’t know how to write keywords in the early stage, you can go directly to many websites that publish ai pictures to see the generation Good quality pictures are then generated to get keywords that fit your model better
别的不说了,新人膜拜大佬··
大佬,这个反向提示词是啥,bad-artist bad-hands-5,没找到
更新了建议资源,你把那个里面包含的下了就行,这只是通用负面而已
可以在hugging face 上搜到,其实不用这么多负面啦
@Terry9993 谢谢大佬解惑
@zhazhahui345好的,谢谢大佬解惑
@Terry9993之前也觉得负面没啥用,现在感觉还是挺关键的
Can you ask what LoRa is used?
Please check the recommended resources, if you download the image and throw it into the image browser of sd, all parameters will be displayed, including the used lora and weight
just Download the Image/Picture itself and Put it in the PNG info thats inside Automatic1111/SD WebUI that will tell you what Lora is used along with everything else
大佬牛逼! 想问下大佬都用那些lora啊? 我试着用你的prompt, 但结果很不一样啊 (T.T) 虽然还是很漂亮. 感谢大佬的更新!
膜拜大佬,这是C站我用过最好的底膜,没有之一。
感觉v9不如v8
论个人我更喜欢0.9的风格,0.8泛化性确实比0.9强很多,但是0.8的出图表现一般,0.9存在过拟,另外不更新是有原因的,只是评论区有人希望能更新我随缘更新了一个版本,不喜欢0.9可以回去用0.8,0.9只是个试验版本
Hey guys I wouldn't download this until they can provide a SafeTensors version. Don't risk it your security is WAY more important than a cool looking model.
exactly this version is no safe with analizer
@Manolas What analizer?
Can i download this now ?
@Love_r_AI No, It is still a ckpt file, can contain malware. You see the file nae is:
fantexiV09beta_fantexiV09beta.ckpt
it should be a *. safetensor
有QQ群吗,我是饭特稀坚实的拥护者!!!!
make it a safetensors
Can I download this now ?
@Love_r_AI you gotta make safetensors
I seem to be doing something wrong, I can't achieve the results above in the images. Maybe there's something wrong with me. Create a detailed guide for this model on how to generate beautiful images, I will be very grateful.
I guess it's still in beta mode that's why you cant make it like that
要怎么才能躲开 xiodf3130 的毒害?
设置里面可以屏蔽用户
退网
隐藏了 看着就难受
@LHOOQ 屏蔽不掉,能屏蔽就没这个问题了
屏蔽他 刷新网页就行
建议见一次举报一次
我手贱!!!!!!
头麻了
笑裂了
没有hires倍数,但是有Denoising strength,up的例图全是图生图吗?ps:这种情况下一般都还原不了大佬的例图……
把作者的图片保存然后PNG图片信息查看然后发到文生图就行
画面精细度提升了不少,但手在hire fix的时候常常会把手修复成脚,手脚的崩坏也都挺严重
请问可以上safe版本么,我以前中过病毒不太敢用这个版的:D
上传太慢,下个版本应该会搞成safe版
自己用转换器转换下就可以了喵
啥意思,还能中毒啊,
can someone do a 0.9/1.0 Anime version as well just asking
用了你的模型,现在身体一天不如一天
大佬啥时候出新的底模啊!您的底模是真的很优秀
"Anyone who doesn't read such a long introduction will be dragged out and ..."
My good sir, I appreciate your humor.
有神快拜,大佬真的是神人啊,
如果方便,还想请教你一下额问题啊,
做出来的模型一时还不是那么顺心。
谢谢大佬。
哎呀,少有得自家福利模型,哈哈,必须支持啊
will you make a pony version? thanks
I use krita where do I have to place the Checkpoint Merge ¿?
This is undoubtedly a very very sexy model! I really liked this cool, very expressive art style with an Asian touch and excellent anatomy with almost no glitches. I am so impressed by such an impressive beauty that I also turn a blind eye to the total feminine focus inherent in this model. Excellent! Thanks!
Nice
评论区问的一律拖出去斩首!😡
Do you plan on creating a ILL or XL version? <3
Details
Files
fantexiV09beta_fantexiV09beta.ckpt
Mirrors
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
fantexiV09beta_fantexiV09beta.ckpt
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



















