V1
An attempt to create a more robust, photorealistic, and capable model. Made with time and love.
定制，代练，付费教学都可以加v: a3281448091 不闲聊 备注sd
My Personal Configuration:
Steps > 28
CFG Scale 7
Sampler: Euler, Euler A, DPM++ 2M Karras, DPM++ SDE Karras
Size: 512x768 or 768x512
Hires upscaler: R-ESRGAN 4x+ or 4x-UltraSharp
Hires upscale: 2
Hires steps: 15
Denoising strength: 0.2~0.5
CFG scale: 6-8
clip skip 2
(for optimal results) Recommended using deepnegative, afterdetailer, betterhands (lyco).
Join my discord server for support! https://discord.gg/h2K2wTr3Dj
Description
FAQ
Comments (10)
为什么这种模型都是这张脸，为什么。。
因为用的是一个人的照片训练的呗
@skalerbrad392 压根就不是训练的，是合并的。CHECKPOINT MERGE 把不同的模型控制权重融合而来。
动态是怎么做的
mov2mov插件
不眨眼睛，太诡异了
Hi, I have a well paid job opportunity with one of our company projects in AI art prompt engineering that you may be interested in.
If you might be interested in discussing this further, please reach out via discord on: mrgunnar
Or alternatively, I can provide you an email address to contact me on.
Many thanks,
Josh
doesnt work well with male generations and male loras
Heey! Great work! Bet you have experience my team needs for our project. How about we collaborate?
If you're interested, could you share your email or Telegram to discuss this?