search

nv-nguyen / nope

[CVPR 2024] PyTorch implementation of NOPE: Novel Object Pose Estimation from a Single Image
182 stars 11 forks source link

VAE model #5

Closed GokulSoman closed 8 months ago

GokulSoman commented 1 year ago

Hi,

I am trying to run the script for training. I looks as if you are using a huggingface model for VAE, using diffusers.AutoencoderKL

But I am not able to access the stable-diffusion-v1-5 model using AutoencoderKL.from_config ("error no config json is present")

I tried changing from autoencoder to StableDiffusionPipeline in diffusers, and using trained weights from runwayml/stable-diffusion-v1-5 , but this class StableDiffusionPipeline do not have an encode method.

Would be glad if you can help fix this issue.

Thanks, Gokul

nv-nguyen commented 8 months ago

Hi, I fixed it here.