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 86 HQ & manually cropped face-focused images!
Recommended strength :1.0-1.3 depending if using solo or 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!
If you're having difficulty, try adding the following tags:
chibi inset + blank eyes
Twitter: https://twitter.com/Vinbee_
Ko-fi: https://ko-fi.com/vinbee/commissions
PayPal: https://www.paypal.com/paypalme/Vinbeez?country.x=ES&locale.x=es_ES
𝐯𝟏.0 - 𝐏𝐮𝐛𝐥𝐢𝐜 𝐑𝐞𝐥𝐞𝐚𝐬𝐞
Trained on 86 HQ images (@repeats x2) 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
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights.