sorrow1990出品
Recently updated on 28 7 月, 2023 at 03:17 上午
Previous
Next
作者原文
先看说明!!!
qq群号:301188613 也请多多关注抖音账号:lora girl。
闲聊:大家好,我是小沙弥,秋名山老司机,开车从来不减速。
(XSM就是我昵称的缩写,lora girl是我愚蠢的小宝贝)
QvQ这是我夏姬八乱搞的大模型,希望大家喜欢。
因为电脑配置原因,跑不出最佳效果,示例图将就看吧,让别人也帮忙跑了几张。包含一些涩涩内容,素材丰富哦!涩图什么的就不方便发了。
特别感谢我的朋友:ℳ๓₯㎕.
特别鸣谢作者:【chocolate 、Showmaker11】 等模型作者
欢迎大家积极返图或者入群以及加抖音交流,谢谢!
例图参数目前大部分填写了.
说明:因为上传太费劲,我上传的模型是FP32的修剪版本。原始版本在这里:liblibAI.
低配显卡推荐启用ADetailer这个修手修脸插件,我也用了的。
负面提示词推荐启用嵌入式文件:EasyNegativeV2, BadNegAnatomyV1-neg, badhandv4,Negfeet-neg 这四个就够了
推荐参数:
•vae:vae-ft-mse-840000-ema-pruned 、vqgan_cfw_00011_vae_only.
•采样:DDIM, DMP++2M SDE, DMP++2M SDE Karras, DMP++2M Karras.
•步数:30~50
•高分辨率修复:20步以上
•放大算法:4x-UltraSharpSP+8xPSNR+8x_NMKD-Superscale_150000_G等搭配使用。
•重绘幅度:0.2~0.5
•基础分辨率:512*768、960*512等,横屏反过来。
•放大倍数:1.5倍以上
•cfg:7(有一个CFG插件可以增加细节,CFG-Schedule-for-Automatic1111-SD 懂的都懂)
推荐lora:
add_detail、Detail Tweaker、GoodHands-beta2、PAseerCloudV1。
推荐的人物lora:小怡同学。
推荐embedding嵌入式文件:
EasyNegativeV2, BadNegAnatomyV1-neg, badhandv4, ng_deepnegative_v1_75t,Negfeet-neg。
————————————————————————————————————————————————————————————————————————————————
Attention:
QQ Group Number: 301188613
Also, please follow the TikTok account: lora girl.
Casual Chat: Hello, everyone. I'm Xiaoshami, a skilled driver on the Autumn Mountain.
I never slow down while driving. (XSM is the abbreviation of my nickname, and lora girl is my silly little sweetheart.)
QvQ This is actually a model I casually and randomly put together. Due to my computer's configuration, I couldn't achieve the best performance.
So, please bear with the sample images. Some friends helped to run a few images as well.
contains some sex content, rich material oh! The sex picture or something is not easy to send.
PS:Special thanks to my friend: ℳ๓₯㎕.
You are welcome to actively contribute images, join the group, or exchange on TikTok. Thank you!
Instructions:
The model I uploaded was a pruned version of FP32 because it was too laborious to upload!!!The original version is here:liblibAI.
Low graphics card recommended to enable the ADetailer hand repair face plug-in, I also used.Example diagram parameters are mostly filled in now.
For negative keywords, it is recommended to use the embedded files:
EasyNegativeV2, BadNegAnatomyV1-neg, badhandv4, Negfeet-neg. These four are sufficient.
Recommended settings:
• VAE: vae-ft-mse-840000-ema-pruned, vqgan_cfw_00011_vae_only. • Sampling: DDIM, DMP++2M SDE, DMP++2M SDE Karras, DMP++2M Karras. • Steps: 30~50.
• High-resolution restoration: Over 20 steps. • Upscaling algorithm: Use combinations such as 4x-UltraSharpSP+8xPSNR+8x_NMKD-Superscale_150000_G. • Redrawing magnitude: 0.2~0.5.
• Base resolution: 512x768, 960x512, etc., flipped horizontally.
• Magnification factor: Over 1.5x.
• CFG: 7 (There is a CFG plugin that can increase details, CFG-Schedule-for-Automatic1111-SD, those who understand will know).
Recommended lora: add_detail, Detail Tweaker, GoodHands-beta2, PAseerCloudV1.
Recommended lora character: 小怡同学。.
Recommended embedding files: EasyNegativeV2, BadNegAnatomyV1-neg, badhandv4, ng_deepnegative_v1_75t, Negfeet-neg.
资源下载
下载价格免费
原文链接:https://cj.suclub.top/4661.html,转载请注明出处。
请先
!