Skip to content

GitLab

Unverified Commit d83d35c1 authored by Chen Mingyi's avatar Chen Mingyi Committed by GitHub
Browse files

Fix bug with VAE slicing in autoencoder_dc.py (#12343)

parent 843355f8
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
src/diffusers/models/autoencoders/autoencoder_dc.py
View file @ d83d35c1
...@@ -617,7 +617,7 @@ class AutoencoderDC(ModelMixin, ConfigMixin, FromOriginalModelMixin): ...@@ -617,7 +617,7 @@ class AutoencoderDC(ModelMixin, ConfigMixin, FromOriginalModelMixin):
returned. returned.
""" """
if self.use_slicing and z.size(0) > 1: if self.use_slicing and z.size(0) > 1:
decoded_slices = [self._decode(z_slice).sample for z_slice in z.split(1)] decoded_slices = [self._decode(z_slice) for z_slice in z.split(1)]
decoded = torch.cat(decoded_slices) decoded = torch.cat(decoded_slices)
else: else:
decoded = self._decode(z) decoded = self._decode(z)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment