a merge with loras trained on hundreds of midjourney niji expressive images with variety of emotions, doesn't look as good but it's allright. Add 'toothy expression' for more pronounced teeth but it's hard to get it right. Can only make humans and humanoids at the moment, i'll update this model if i have time I Use hires. fix, upscale latent, denoising 0.5, hires steps 20, upscale by 2 . Clip skip 2 .
I use night sky yozora VAE in the examples https://civitai.com/api/download/models/14459?type=VAE
if you like the models, please consider supporting me on, i will continue to upload more cool stuffs in the future