Mesugaki - Facial Expression
This model is a DoRA LoCON (Weight Decompose LoRA LoCON). It requires A1111 1.9.0 or newer. For Forge installations, apply the specified PR.
Trained on 180 HQ & manually cropped "Mesugaki" face-focused images!
Works best at :0.8 strength when mixing with other Lora's.
Training data does not contain any NSFW images!
V2 will add even more training data.Be sure to use the proper tags in order to generate the expression correctly!
Follow me on my socials!
Twitter: https://twitter.com/Vinbee_
Have a request? Commission me on ko-fi! โ
Ko-fi: https://ko-fi.com/vinbee/commissions
You can also support my work via PayPal!
PayPal: https://www.paypal.com/paypalme/Vinbeez?country.x=ES&locale.x=es_ES
Description
๐ฏ๐.๐ - Private (Skipped)
๐ฏ๐.๐ - ๐๐ฎ๐๐ฅ๐ข๐ ๐๐๐ฅ๐๐๐ฌ๐
Trained on 180 HQ images for the most authentic quality possible
Manually upscaled & cropped all images to fit PonyXL standards
Switched from 32/32 Network alpha/dim to 8/4 to lower file size
FAQ
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.