Diffusers v0.12 removed the `ema_model.averaged_model` attribute

teticio / audio-diffusion

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

GNU General Public License v3.0

707 stars 69 forks source link

Closed shiehn closed 1 year ago

shiehn commented 1 year ago

Diffusers v0.12 removed the ema_model.averaged_model attribute which is referenced in train_unet.py

Screenshot 2023-02-02 at 1 46 24 AM

teticio commented 1 year ago

Thanks again! Fixed it.