Model info: https://civitai.com/models/84604/nk15

if you use this model in your diffusers, show some AutoencoderKL errors, Don't worry, just use the codes below, you can still generate images :)

modelid="digiplay/nk15_diffusers"

from diffusers.models import AutoencoderKL

vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")

pipe = DiffusionPipeline.from_pretrained(modelid, vae=vae)