robbon

[stable-diffusion-x4-upscaler] Use pretrain VAE to encode a 512x512 image to latent space get nan, the image has been normalized to [-1,1]

5

I have downloaded the stable-diffusion-x4-upscaler pre-train model from https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler I try to fine-tune the upscaler model with my own data, however, I find when I encode the 512x512 image to...